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

    Neuronpedia

    INDEX
    Explanations

    license

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .nextElement
    -0.07
    prepare
    -0.06
    =msg
    -0.06
    specified
    -0.06
    孅
    -0.06
     ballot
    -0.06
     Ultimate
    -0.06
    (repository
    -0.06
     technological
    -0.06
    WARE
    -0.06
    POSITIVE LOGITS
     persu
    0.08
    🇴
    0.07
    华润
    0.07
     rais
    0.07
     مصر
    0.07
    _crit
    0.06
    走势图
    0.06
    ombat
    0.06
    评议
    0.06
    :invoke
    0.06
    Act Density 0.001%

    No Known Activations