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

    Neuronpedia

    INDEX
    Explanations

    Wayne

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    污染防治
    -0.08
    ρ
    -0.07
     tempList
    -0.07
     love
    -0.07
    Prot
    -0.07
    rup
    -0.07
     Gibbs
    -0.07
     Pos
    -0.07
     Loved
    -0.07
    GroupName
    -0.06
    POSITIVE LOGITS
    _BAR
    0.07
     carved
    0.07
     yönelik
    0.07
    インタ
    0.07
    马路
    0.07
     adolescente
    0.07
    ﾅ
    0.07
     intptr
    0.07
     recreational
    0.07
     источник
    0.07
    Act Density 0.003%

    No Known Activations