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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GO
    -0.07
    emony
    -0.07
    ô
    -0.06
     national
    -0.06
    Ø
    -0.06
     Sometimes
    -0.06
     Universities
    -0.06
     Perhaps
    -0.06
    щий
    -0.06
     punishments
    -0.06
    POSITIVE LOGITS
     for
    0.08
    textInput
    0.08
     شب
    0.07
     ('\
    0.07
     أف
    0.07
    NSData
    0.06
     flock
    0.06
    _fore
    0.06
    Colorado
    0.06
     beauty
    0.06
    Act Density 0.010%

    No Known Activations