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

    Neuronpedia

    INDEX
    Explanations

    action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pornôs
    -0.07
     Sweat
    -0.07
    iyle
    -0.07
    iration
    -0.07
    LIBINT
    -0.06
    상위
    -0.06
    된다
    -0.06
    .Menu
    -0.06
    ível
    -0.06
    ЕР
    -0.06
    POSITIVE LOGITS
     Bik
    0.07
     denying
    0.06
     باشگاه
    0.06
     puzz
    0.06
     yog
    0.06
    ParseException
    0.06
     eigentlich
    0.06
     okol
    0.06
     deny
    0.06
     obvious
    0.06
    Act Density 0.012%

    No Known Activations