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

    Neuronpedia

    INDEX
    Explanations

    affection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LoadIdentity
    -0.08
     Zar
    -0.08
     yan
    -0.07
     pasar
    -0.07
    amar
    -0.07
     Yaş
    -0.07
     Fuji
    -0.06
     blockers
    -0.06
     joined
    -0.06
     catalyst
    -0.06
    POSITIVE LOGITS
     affection
    0.08
     touching
    0.08
     Benton
    0.07
    ئت
    0.06
    FFE
    0.06
     indoors
    0.06
    iff
    0.06
    �
    0.06
    uffs
    0.06
     fillColor
    0.06
    Act Density 0.003%

    No Known Activations