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

    Neuronpedia

    INDEX
    Explanations

    &

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bgcolor
    -0.07
     aún
    -0.07
    933
    -0.07
    -fold
    -0.07
    -third
    -0.06
     fazer
    -0.06
     öner
    -0.06
    _ATTACH
    -0.06
    �
    -0.06
     будів
    -0.06
    POSITIVE LOGITS
    oliberal
    0.07
    Want
    0.06
     sensed
    0.06
    Rotate
    0.06
    +=
    0.06
     prime
    0.06
    MENU
    0.06
     Lindsey
    0.06
    :+
    0.06
     consume
    0.06
    Act Density 0.002%

    No Known Activations