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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Json
    -0.06
     Cheat
    -0.06
     rave
    -0.06
    cars
    -0.06
    먹
    -0.06
    itarian
    -0.06
     grosse
    -0.06
    AP
    -0.06
     Wheels
    -0.06
    YYY
    -0.06
    POSITIVE LOGITS
    Sept
    0.07
    /:
    0.06
     alpha
    0.06
     غير
    0.06
    _HELP
    0.06
    /msg
    0.06
    ishes
    0.06
     GetEnumerator
    0.06
     şiş
    0.06
     Pepsi
    0.06
    Act Density 0.000%

    No Known Activations