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

    Neuronpedia

    INDEX
    Explanations

    /**

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Daw
    -0.08
     spending
    -0.07
     PI
    -0.07
     dan
    -0.07
    оу
    -0.06
     kvinde
    -0.06
     dick
    -0.06
     liền
    -0.06
    !↵
    -0.06
     loaf
    -0.06
    POSITIVE LOGITS
     Euros
    0.07
     REPLACE
    0.06
     Vive
    0.06
    csrf
    0.06
    .toBe
    0.06
    .assertRaises
    0.06
     UserRole
    0.06
    ์เซ
    0.06
    verty
    0.06
    ="<?=$
    0.06
    Act Density 0.005%

    No Known Activations