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

    Neuronpedia

    INDEX
    Explanations

    programming errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opi
    -0.07
    allenge
    -0.07
    .bd
    -0.07
    ()↵↵
    -0.07
    رك
    -0.06
    卖
    -0.06
     hấp
    -0.06
     Frau
    -0.06
    male
    -0.06
    Apellido
    -0.06
    POSITIVE LOGITS
    Granted
    0.07
     (+
    0.06
    読
    0.06
     Tolkien
    0.06
    еної
    0.06
    /pages
    0.06
    ЕТ
    0.06
    ิภาพ
    0.06
     migrating
    0.06
     ))
    0.06
    Act Density 0.013%

    No Known Activations