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

    Neuronpedia

    INDEX
    Explanations

    Code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ColumnType
    -0.07
    孙
    -0.07
    WF
    -0.07
     BANK
    -0.07
     summarizes
    -0.06
     Gutenberg
    -0.06
    กราคม
    -0.06
     jerk
    -0.06
    雅黑
    -0.06
    _function
    -0.06
    POSITIVE LOGITS
    患
    0.07
    edics
    0.06
     roz
    0.06
    _ADMIN
    0.06
    itos
    0.06
    	defer
    0.06
    ्रश
    0.06
     researchers
    0.06
    helpers
    0.06
     encounters
    0.06
    Act Density 0.037%

    No Known Activations