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

    Neuronpedia

    INDEX
    Explanations

    Errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ",
↵
    -0.07
    _INTERRUPT
    -0.07
     sel
    -0.07
    Ỉ
    -0.07
    ”↵↵
    -0.07
    ế
    -0.07
    篮
    -0.06
     '/');↵
    -0.06
    ='<
    -0.06
     Conserv
    -0.06
    POSITIVE LOGITS
    鹴
    0.08
    眼看
    0.07
    딉
    0.07
    קו
    0.07
     Sto
    0.07
     Hulu
    0.07
     guys
    0.07
     monet
    0.07
    ꉂ
    0.07
    排除
    0.07
    Act Density 0.001%

    No Known Activations