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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    excel
    -0.07
     REPRESENT
    -0.07
    preserve
    -0.06
    ̆
    -0.06
    PrivateKey
    -0.06
    ít
    -0.06
     суп
    -0.06
     olm
    -0.06
    _players
    -0.06
    _DETECT
    -0.06
    POSITIVE LOGITS
     завер
    0.07
     sanat
    0.07
    ()+
    0.06
    delay
    0.06
     ।
    0.06
     upward
    0.06
     catcher
    0.06
    faculty
    0.06
    ≡≡
    0.06
     sử
    0.06
    Act Density 0.015%

    No Known Activations