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

    Neuronpedia

    INDEX
    Explanations

    Code punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comic
    -0.06
    INSTANCE
    -0.06
    泉
    -0.06
    column
    -0.06
    Beautiful
    -0.06
    ’all
    -0.06
    、​
    -0.06
     paris
    -0.06
    _read
    -0.06
    Toolbar
    -0.06
    POSITIVE LOGITS
    Prefs
    0.08
     Bran
    0.06
    _DER
    0.06
    _CLK
    0.06
    $",
    0.06
    &);↵↵
    0.06
     COMMENT
    0.06
    .Sys
    0.06
    .IsSuccess
    0.06
    Professional
    0.06
    Act Density 0.006%

    No Known Activations