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

    Neuronpedia

    INDEX
    Explanations

    various topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ירו
    -0.07
     furry
    -0.07
     فإذا
    -0.07
    .GetBytes
    -0.07
     edged
    -0.07
     bpp
    -0.07
     dados
    -0.07
    דירות
    -0.07
    idad
    -0.06
     vielen
    -0.06
    POSITIVE LOGITS
     goodwill
    0.07
    -account
    0.07
    Program
    0.07
     Danish
    0.07
    一开始
    0.07
    ﹰ
    0.06
    뗄
    0.06
    BBC
    0.06
    介入
    0.06
    二线
    0.06
    Act Density 0.087%

    No Known Activations