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

    Neuronpedia

    INDEX
    Explanations

    face

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     güvenlik
    -0.07
    行政
    -0.07
    ()}</
    -0.06
     meteor
    -0.06
     MF
    -0.06
     commissioner
    -0.06
    North
    -0.06
    ูไ
    -0.06
     Ге
    -0.06
    =""></
    -0.06
    POSITIVE LOGITS
    andidates
    0.07
     nguyện
    0.06
    *e
    0.06
    รอง
    0.06
     limited
    0.06
    __))↵
    0.06
     prze
    0.06
     utilized
    0.06
     eh
    0.06
    Modes
    0.06
    Act Density 0.005%

    No Known Activations