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

    Neuronpedia

    INDEX
    Explanations

    terms related to obstacles and barriers in various contexts

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

    [word] as a [noun]

    np_acts-logits-general · gemini-2.0-flash

    challenges, necessities, or tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.71
    omitempty
    -0.70
    FormBuilder
    -0.63
    ajevo
    -0.61
    mich
    -0.61
    SequentialGroup
    -0.60
    ++
    -0.60
    racene
    -0.59
    ">
    -0.59
     indestru
    -0.58
    POSITIVE LOGITS
     bagi
    0.80
     geworden
    0.70
     addition
    0.58
     zugleich
    0.58
     unto
    0.57
     for
    0.57
     rather
    0.57
     parmi
    0.53
    的一部分
    0.52
     بالنسبة
    0.52
    Act Density 0.535%

    No Known Activations