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
    rollable
    -0.08
     exchanged
    -0.07
     develops
    -0.07
     Aw
    -0.07
    济
    -0.06
     downloading
    -0.06
     Scotch
    -0.06
     FAMILY
    -0.06
     Duffy
    -0.06
    gewater
    -0.06
    POSITIVE LOGITS
    WithError
    0.07
    無し
    0.06
    独
    0.06
    .VideoCapture
    0.06
    对象
    0.06
     обмеж
    0.06
    懂
    0.06
    .ALL
    0.06
    。不
    0.06
     
    0.06
    Act Density 0.003%

    No Known Activations