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

    Neuronpedia

    INDEX
    Explanations

    about on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Scr
    -0.07
    乡
    -0.06
    ),↵↵
    -0.06
    Pack
    -0.06
    _ptrs
    -0.06
        ↵    ↵    ↵
    -0.06
    �
    -0.06
    activated
    -0.06
    يل
    -0.06
    ยนต
    -0.06
    POSITIVE LOGITS
     mechanics
    0.07
    林
    0.07
     مطال
    0.07
    dre
    0.07
    ahoo
    0.07
     jue
    0.06
    vertiser
    0.06
     Thunder
    0.06
    _dataframe
    0.06
    iere
    0.06
    Act Density 0.015%

    No Known Activations