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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ChatColor
    -0.06
     Kaynak
    -0.06
     *****
    -0.06
    _BATCH
    -0.06
    타이
    -0.06
     bahwa
    -0.06
    EMPLARY
    -0.06
     فرمان
    -0.06
    gold
    -0.06
     patriarch
    -0.06
    POSITIVE LOGITS
     csrf
    0.07
     dangerous
    0.06
     picked
    0.06
     coal
    0.06
     picking
    0.06
     dick
    0.06
    WH
    0.06
     Rus
    0.06
     needed
    0.06
     Calcium
    0.06
    Act Density 0.009%

    No Known Activations