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

    Neuronpedia

    INDEX
    Explanations

    34

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gros
    -0.07
     ویژگی
    -0.07
    Additional
    -0.07
     durable
    -0.07
    .projects
    -0.07
     дис
    -0.06
     disrespectful
    -0.06
    _cs
    -0.06
    [left
    -0.06
     VE
    -0.06
    POSITIVE LOGITS
     Wildlife
    0.07
     Май
    0.07
    ΟΚ
    0.07
    auled
    0.06
    _GUI
    0.06
     ServiceException
    0.06
    edor
    0.06
     文件
    0.06
     filed
    0.06
    ELL
    0.06
    Act Density 0.000%

    No Known Activations