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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ikal
    -0.07
    alloween
    -0.07
     gadgets
    -0.07
     dateTime
    -0.06
    Unload
    -0.06
    lux
    -0.06
    XmlNode
    -0.06
    cats
    -0.06
     balance
    -0.06
    zing
    -0.06
    POSITIVE LOGITS
    ิ์
    0.07
    arian
    0.06
    ندگی
    0.06
    Tro
    0.06
    тою
    0.06
     了
    0.06
     Outlet
    0.06
    ーブ
    0.06
     Chrom
    0.06
     »↵↵
    0.06
    Act Density 0.005%

    No Known Activations