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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    这样的
    -0.08
    MAR
    -0.07
    Italic
    -0.07
    Beta
    -0.07
    Pairs
    -0.07
     herself
    -0.06
    иск
    -0.06
     eagerly
    -0.06
    'h
    -0.06
     suddenly
    -0.06
    POSITIVE LOGITS
    BaseContext
    0.06
     PARAM
    0.06
    _ANY
    0.06
     спе
    0.06
     francouz
    0.06
    bbing
    0.06
    .DecimalField
    0.06
     chị
    0.06
    _Task
    0.06
    量
    0.06
    Act Density 0.003%

    No Known Activations