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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue or interaction between characters

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

    names and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.75
     BoxFit
    -0.75
    ValueStyle
    -0.69
    +#+#
    -0.67
    majánló
    -0.66
    BibitemShut
    -0.64
     चीज़ों
    -0.63
    RTLR
    -0.63
    iſchen
    -0.63
    niſſe
    -0.61
    POSITIVE LOGITS
     Савезне
    0.38
     astore
    0.30
     partnered
    0.29
    fVar
    0.29
    instancetype
    0.29
    searched
    0.28
     SimpleName
    0.28
     querida
    0.28
    ulement
    0.27
     froid
    0.26
    Act Density 0.025%

    No Known Activations