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

    Neuronpedia

    INDEX
    Explanations

    .h

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ozem
    -0.07
     maur
    -0.07
    _preference
    -0.07
    -purple
    -0.07
     slav
    -0.06
     vững
    -0.06
     vegas
    -0.06
    olia
    -0.06
    積
    -0.06
     Yük
    -0.06
    POSITIVE LOGITS
    았다
    0.07
     NASCAR
    0.06
    roc
    0.06
    �
    0.06
    :::|
    0.06
    EMPL
    0.06
    ******↵↵
    0.06
    _ml
    0.06
     abst
    0.06
     twitch
    0.06
    Act Density 0.002%

    No Known Activations