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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الدولة
    -0.07
    ारण
    -0.06
     Shots
    -0.06
     Arn
    -0.06
    (home
    -0.06
     fir
    -0.06
    372
    -0.06
    455
    -0.06
    Redux
    -0.06
    尘
    -0.06
    POSITIVE LOGITS
    sender
    0.07
    inte
    0.06
     doğrult
    0.06
     biliyor
    0.06
     "__
    0.06
    Het
    0.06
     unread
    0.06
    .CASCADE
    0.06
    isbury
    0.06
    ีฬา
    0.06
    Act Density 0.131%

    No Known Activations