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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     from
    -0.07
    Extract
    -0.07
    Lbl
    -0.07
    logout
    -0.07
    Income
    -0.06
    aktu
    -0.06
    fte
    -0.06
    William
    -0.06
    Paragraph
    -0.06
    7
    -0.06
    POSITIVE LOGITS
    _timezone
    0.07
     throm
    0.07
    册
    0.07
    .done
    0.06
     площад
    0.06
     pics
    0.06
    vor
    0.06
     남자
    0.06
    НИ
    0.06
     telefon
    0.06
    Act Density 0.114%

    No Known Activations