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

    Neuronpedia

    INDEX
    Explanations

    mathematical isomorphism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ctx
    -0.08
    全部
    -0.07
     involve
    -0.07
    意见反馈
    -0.07
    took
    -0.07
    财政
    -0.07
    扶持
    -0.07
     Turns
    -0.07
    ssé
    -0.07
     Given
    -0.06
    POSITIVE LOGITS
    золот
    0.08
    LineColor
    0.08
    _PROD
    0.07
    텣
    0.07
    饥饿
    0.07
     liqu
    0.07
    גיד
    0.07
    .MaxValue
    0.07
    乐
    0.07
     chiar
    0.07
    Act Density 0.005%

    No Known Activations