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

    Neuronpedia

    INDEX
    Explanations

    variables in code/math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ँग
    -0.09
    (image
    -0.07
    ubiri
    -0.07
     image
    -0.07
    ंगा
    -0.07
     alternativa
    -0.07
    וכל
    -0.07
    _IMAGE
    -0.07
     immens
    -0.07
     konkr
    -0.07
    POSITIVE LOGITS
     lotus
    0.08
    க்கம்
    0.08
     snapped
    0.07
    .prec
    0.07
     વૃ
    0.07
    瞬
    0.07
    recommended
    0.07
     اللح
    0.07
     রাখতে
    0.07
    meteor
    0.07
    Act Density 0.013%

    No Known Activations