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

    Neuronpedia

    INDEX
    Explanations

    gist URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PARSER
    -0.07
     predicts
    -0.07
    explode
    -0.07
    ℬ
    -0.07
    �
    -0.07
     inorder
    -0.07
    orie
    -0.07
     אות
    -0.07
     kHz
    -0.07
    ɯ
    -0.07
    POSITIVE LOGITS
    lıklar
    0.07
    gn
    0.07
    Debe
    0.07
    ))+
    0.06
    crement
    0.06
    出炉
    0.06
     ey
    0.06
     =>
↵
    0.06
    旒
    0.06
    出门
    0.06
    Act Density 0.003%

    No Known Activations