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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -solving
    -0.08
     plá
    -0.06
     stati
    -0.06
    Criterion
    -0.06
    更
    -0.06
    .attack
    -0.06
    明
    -0.06
    ‘
    -0.06
    ��
    -0.06
    .’
    -0.06
    POSITIVE LOGITS
     McG
    0.07
    DefaultCellStyle
    0.07
    gend
    0.06
    SELF
    0.06
     Shar
    0.06
     passwd
    0.06
    )const
    0.06
     piracy
    0.06
    ROADCAST
    0.06
    GeneratedValue
    0.06
    Act Density 0.018%

    No Known Activations