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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    posing
    -0.07
    ült
    -0.07
    蔈
    -0.07
     foresee
    -0.07
    𫮃
    -0.07
     obsession
    -0.06
    蹚
    -0.06
    嗞
    -0.06
    lıklar
    -0.06
    宵
    -0.06
    POSITIVE LOGITS
    _support
    0.08
    (ver
    0.07
    (word
    0.07
    要好好
    0.07
     empowerment
    0.07
    与
    0.07
    Maria
    0.07
    惊喜
    0.07
    )(*
    0.07
    armor
    0.07
    Act Density 0.106%

    No Known Activations