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

    Neuronpedia

    INDEX
    Explanations

    News reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    레스
    -0.08
     관심
    -0.07
     acute
    -0.07
    ectors
    -0.07
     opinions
    -0.06
    Bus
    -0.06
    ivos
    -0.06
    ��
    -0.06
    偶
    -0.06
    weise
    -0.06
    POSITIVE LOGITS
     싸
    0.07
    :maj
    0.06
    role
    0.06
    .consumer
    0.06
     blij
    0.06
    .Args
    0.06
     demokrat
    0.06
    .ant
    0.06
     افز
    0.05
    .getLogin
    0.05
    Act Density 0.033%

    No Known Activations