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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lately
    -0.06
    /logging
    -0.06
    !]
    -0.06
     putting
    -0.06
     cruc
    -0.06
     slammed
    -0.06
    (components
    -0.06
    _billing
    -0.06
     ремон
    -0.06
     handling
    -0.06
    POSITIVE LOGITS
    _HELPER
    0.07
     distra
    0.07
    UDGE
    0.07
    μως
    0.07
     conosc
    0.06
    (case
    0.06
    AGED
    0.06
    孩
    0.06
     Constitution
    0.06
    poň
    0.06
    Act Density 0.158%

    No Known Activations