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

    Neuronpedia

    INDEX
    Explanations

    --

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    改装
    -0.07
     putt
    -0.07
    redux
    -0.06
    ☽
    -0.06
    .mov
    -0.06
    领导班子
    -0.06
     ef
    -0.06
    walk
    -0.06
    sie
    -0.06
     gre
    -0.06
    POSITIVE LOGITS
    忘れ
    0.07
    Петербур
    0.07
    обще
    0.07
    .Low
    0.07
     Gerry
    0.07
     Strong
    0.07
    娜
    0.07
     tol
    0.07
     serum
    0.06
     nausea
    0.06
    Act Density 0.002%

    No Known Activations