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

    Neuronpedia

    INDEX
    Explanations

    assessments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /v
    -0.07
     Umb
    -0.07
    .spacing
    -0.06
     Kub
    -0.06
    ':''
    -0.06
    ьте
    -0.06
    桌
    -0.06
     профес
    -0.06
    chrom
    -0.06
    итив
    -0.06
    POSITIVE LOGITS
    (Func
    0.07
     invoice
    0.07
     ).↵
    0.07
     人
    0.06
    ohl
    0.06
    MASK
    0.06
    .)↵
    0.06
    (DATA
    0.06
    检测
    0.06
    ish
    0.06
    Act Density 0.001%

    No Known Activations