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

    Neuronpedia

    INDEX
    Explanations

    themes related to social acceptance and personal reflection

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

    ways to handle things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteAttribute
    -0.60
    awtextra
    -0.47
     FU
    -0.43
     dian
    -0.43
     Wig
    -0.42
    ┛
    -0.42
    PerformLayout
    -0.42
     useParams
    -0.41
     flops
    -0.41
    cupertino
    -0.40
    POSITIVE LOGITS
    хьтан
    0.74
     autorytatywna
    0.58
    elemField
    0.56
     informée
    0.51
     esternos
    0.48
    RenderAtEndOf
    0.47
    Jîn
    0.47
    Derbyniad
    0.42
     intStringLen
    0.40
     internetowa
    0.40
    Act Density 0.045%

    No Known Activations