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

    Neuronpedia

    INDEX
    Explanations

    Code/Legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     admiration
    -0.07
    پی
    -0.06
    میر
    -0.06
    (alias
    -0.06
    -feedback
    -0.06
    gement
    -0.06
    roke
    -0.06
    emouth
    -0.06
    وس
    -0.06
    rede
    -0.06
    POSITIVE LOGITS
     ウ
    0.06
     manip
    0.06
    (Encoding
    0.06
    Tên
    0.06
    .SuppressLint
    0.06
    (Temp
    0.06
    (short
    0.06
     vulnerability
    0.06
     Vulner
    0.06
    .TableLayoutPanel
    0.06
    Act Density 0.000%

    No Known Activations