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

    Neuronpedia

    INDEX
    Explanations

    oscopic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fit
    -0.07
    ϒ
    -0.07
    ture
    -0.07
    غياب
    -0.07
    Ye
    -0.07
    st
    -0.07
     View
    -0.07
     four
    -0.06
    培
    -0.06
     heaters
    -0.06
    POSITIVE LOGITS
    fällig
    0.09
    쩠
    0.08
    款项
    0.08
    רכה
    0.07
    InnerText
    0.07
    _PROJECT
    0.07
    كني
    0.07
     horrified
    0.07
    Thanks
    0.07
    .params
    0.07
    Act Density 0.004%

    No Known Activations