Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the use of prepositions, particularly "in" and "out of," to discuss spatial and contextual relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    occurrences of the word "in" or other similar prepositions indicating location or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    one in numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.64
     بيها
    -0.60
     Normdatei
    -0.60
    glades
    -0.58
    Enllaces
    -0.55
     tecnici
    -0.55
    nott
    -0.55
     themſelves
    -0.54
    脚注の使い方
    -0.54
    lujah
    -0.54
    POSITIVE LOGITS
     every
    0.73
     ten
    0.65
     five
    0.59
     six
    0.56
    testens
    0.56
     four
    0.55
    ">//
    0.55
     Every
    0.52
     a
    0.50
    ниципа
    0.50
    Act Density 0.023%

    No Known Activations