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
     multimedia
    -0.07
    _CHO
    -0.06
    Overlap
    -0.06
    opath
    -0.06
     ours
    -0.06
    фіка
    -0.06
    hunt
    -0.06
    maker
    -0.06
     theirs
    -0.06
     Vinci
    -0.06
    POSITIVE LOGITS
    ｿ
    0.08
    Mt
    0.07
    _der
    0.06
    ､
    0.06
     článek
    0.06
     semiclass
    0.06
     argc
    0.06
     mak
    0.06
    _shared
    0.06
     г
    0.05
    Act Density 0.081%

    No Known Activations