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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nag
    -0.07
    "For
    -0.07
    .assertNotNull
    -0.07
    空气中
    -0.06
    'av
    -0.06
    ’av
    -0.06
     closely
    -0.06
    _cont
    -0.06
    .getActivity
    -0.06
     allowances
    -0.06
    POSITIVE LOGITS
    面子
    0.07
    塌
    0.07
    SenderId
    0.07
     grant
    0.07
    份
    0.07
    轮融资
    0.07
     sứ
    0.07
     Jugend
    0.07
     learner
    0.07
    EOF
    0.07
    Act Density 0.030%

    No Known Activations