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

    Neuronpedia

    INDEX
    Explanations

    style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fileInfo
    -0.08
     lions
    -0.08
     Pleasant
    -0.07
     religion
    -0.06
     apps
    -0.06
     dn
    -0.06
     داده
    -0.06
     engagement
    -0.06
     obese
    -0.06
     Janet
    -0.06
    POSITIVE LOGITS
    作者
    0.07
    สาย
    0.07
    'er
    0.06
    incre
    0.06
    ailand
    0.06
    -email
    0.06
    첨부
    0.06
    okus
    0.06
    耗
    0.06
    iterr
    0.06
    Act Density 0.003%

    No Known Activations