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

    Neuronpedia

    INDEX
    Explanations

    delinquency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .fname
    -0.07
    كيل
    -0.06
    xcb
    -0.06
    اده
    -0.06
     Walt
    -0.06
    nore
    -0.06
    ationale
    -0.06
    .isNotEmpty
    -0.06
    matches
    -0.06
    ροφορίες
    -0.06
    POSITIVE LOGITS
     chick
    0.08
    üph
    0.08
     повин
    0.08
    .*;
↵
    0.07
    chio
    0.07
     BW
    0.07
    _();↵
    0.07
     Window
    0.07
     NA
    0.07
    ="<
    0.07
    Act Density 0.008%

    No Known Activations