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

    Neuronpedia

    INDEX
    Explanations

    produce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fatal
    -0.08
    ..."↵
    -0.08
    ...",↵
    -0.08
    深入
    -0.07
    戸
    -0.07
     approfond
    -0.07
     fatal
    -0.07
     столк
    -0.07
    =true
    -0.07
    .Det
    -0.07
    POSITIVE LOGITS
     punctuation
    0.11
     Typ
    0.09
     typing
    0.09
     mashed
    0.08
     Revised
    0.08
     pronunciation
    0.08
    semicolon
    0.08
     Updated
    0.08
     revised
    0.08
     Display
    0.07
    Act Density 0.042%

    No Known Activations