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

    Neuronpedia

    INDEX
    Explanations

    passions and interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    1.10
     A
    1.08
     Situation
    0.91
     L
    0.89
     S
    0.88
     M
    0.88
     en
    0.88
     edge
    0.88
    р
    0.86
    Ａ
    0.86
    POSITIVE LOGITS
     fièvre
    1.13
     passions
    1.13
    爱好
    1.13
     đam
    1.11
     beauté
    1.05
     passione
    1.02
     htob
    1.00
     preco
    0.98
    ualitas
    0.97
     године
    0.97
    Act Density 0.426%

    No Known Activations