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

    Neuronpedia

    INDEX
    Explanations

    club

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offences
    -0.06
    omor
    -0.06
    TE
    -0.06
     QFont
    -0.06
     ominous
    -0.06
    resi
    -0.06
     степ
    -0.06
     realize
    -0.06
     proble
    -0.06
     příst
    -0.06
    POSITIVE LOGITS
    """
↵
↵
    0.07
    ğine
    0.07
    (mail
    0.07
    hero
    0.06
     Skate
    0.06
    >();
↵
↵
    0.06
     perpetual
    0.06
    Ten
    0.06
     """
↵
    0.06
    /event
    0.06
    Act Density 0.009%

    No Known Activations