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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Measured
    -0.07
    _figure
    -0.07
    _FOR
    -0.07
    ?>
    -0.07
    sorry
    -0.06
    gc
    -0.06
     slur
    -0.06
    gl
    -0.06
    Bits
    -0.06
    ”,
    -0.06
    POSITIVE LOGITS
     controle
    0.07
    FileInfo
    0.07
    ADF
    0.06
    سیون
    0.06
    ایر
    0.06
     sorunu
    0.06
    ду
    0.06
     respawn
    0.06
    useRalativeImagePath
    0.06
     QDialog
    0.06
    Act Density 0.012%

    No Known Activations