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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guidelines
    -0.07
    _ALLOWED
    -0.06
     Jo
    -0.06
    妇
    -0.06
     суще
    -0.06
    Author
    -0.06
     omit
    -0.06
     Республи
    -0.06
     BEN
    -0.06
    DL
    -0.06
    POSITIVE LOGITS
    ับร
    0.07
     maybe
    0.07
    χρι
    0.06
    [field
    0.06
     collections
    0.06
    ایند
    0.06
     rid
    0.06
    аліз
    0.06
     crem
    0.06
    _response
    0.06
    Act Density 0.087%

    No Known Activations