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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kč
    -0.07
    talk
    -0.07
     راهنم
    -0.06
    gain
    -0.06
    bias
    -0.06
     Rams
    -0.06
    rias
    -0.06
    )");↵
    -0.06
     labelled
    -0.06
    -processing
    -0.06
    POSITIVE LOGITS
    $tpl
    0.07
     😀
    0.06
    .SimpleDateFormat
    0.06
    intValue
    0.06
     Sender
    0.06
     생각
    0.06
    zej
    0.06
    (Integer
    0.06
     yaptı
    0.06
    Sender
    0.06
    Act Density 0.062%

    No Known Activations