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

    Neuronpedia

    INDEX
    Explanations

    judging people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ################################################
    -0.08
    ium
    -0.07
    ��
    -0.06
     Oregon
    -0.06
     그림
    -0.06
    umerator
    -0.06
     allocator
    -0.06
    sembly
    -0.06
     FP
    -0.06
     userDao
    -0.06
    POSITIVE LOGITS
     ヴ
    0.06
    Delayed
    0.06
     λόγ
    0.06
    /Login
    0.06
    .goto
    0.06
    _nth
    0.06
    bildung
    0.06
     Clears
    0.06
    .sigma
    0.05
     Holding
    0.05
    Act Density 0.029%

    No Known Activations