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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jimmy
    -0.08
    uae
    -0.07
     Cone
    -0.07
    首富
    -0.07
    مؤشر
    -0.07
    _aw
    -0.06
    cych
    -0.06
     Wild
    -0.06
    Opening
    -0.06
    机遇
    -0.06
    POSITIVE LOGITS
    _OBJECT
    0.08
    ">{{
    0.07
    --}}↵
    0.07
    _=
    0.07
     progn
    0.07
    괸
    0.07
     interpreted
    0.07
    beck
    0.07
    _glob
    0.07
    .gca
    0.06
    Act Density 0.031%

    No Known Activations