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

    Neuronpedia

    INDEX
    Explanations

    instances of fleeing or escape

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

    Actions of leaving or disappearing

    np_acts-logits-general · gemini-2.0-flash

    leaving or disappearing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IndentedString
    -0.61
    olastic
    -0.58
    ükemmel
    -0.56
    tamia
    -0.54
    AccessorTable
    -0.53
    навли
    -0.52
     ویکی‌پدیای
    -0.52
     FishBase
    -0.51
    </tfoot>
    -0.51
    bernador
    -0.50
    POSITIVE LOGITS
     leaving
    1.75
    leaving
    1.46
     leave
    1.41
    Leaving
    1.41
     Leaving
    1.38
    Leave
    1.26
     Leave
    1.24
     meninggalkan
    1.23
    leave
    1.23
     leaves
    1.23
    Act Density 0.290%

    No Known Activations