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

    Neuronpedia

    INDEX
    Explanations

    Time intervals/scaling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     système
    -0.08
    Bulletin
    -0.07
     word
    -0.06
    figures
    -0.06
     ends
    -0.06
    Separ
    -0.06
     counterparts
    -0.06
     derivative
    -0.06
    "^
    -0.06
     Colorado
    -0.06
    POSITIVE LOGITS
    _title
    0.06
     TI
    0.06
    装
    0.06
    displayName
    0.06
    (Page
    0.06
    enaries
    0.06
     mMap
    0.06
    ?',
    0.06
     olup
    0.06
    reetings
    0.06
    Act Density 0.058%

    No Known Activations