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

    Neuronpedia

    INDEX
    Explanations

    intervening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pin
    -0.07
    cal
    -0.07
     Probability
    -0.07
     Increase
    -0.07
    NSS
    -0.07
    ома
    -0.07
    Modification
    -0.07
    něji
    -0.06
     efficiency
    -0.06
    ыш
    -0.06
    POSITIVE LOGITS
    Senator
    0.07
    _eval
    0.06
     meanwhile
    0.06
     '}
    0.06
    .game
    0.06
    堂
    0.06
     jako
    0.06
    краї
    0.06
    =utf
    0.06
     "~
    0.06
    Act Density 0.012%

    No Known Activations