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

    Neuronpedia

    INDEX
    Explanations

    Add

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relinqu
    -0.06
     Exhaust
    -0.06
    śmy
    -0.06
    aggio
    -0.06
    願
    -0.06
    Trad
    -0.06
     تنظيف
    -0.06
     registrazione
    -0.06
    _RESET
    -0.06
    _power
    -0.06
    POSITIVE LOGITS
     isn
    0.08
    (items
    0.07
    ,uint
    0.07
    =s
    0.07
    sis
    0.07
    difference
    0.07
     chick
    0.07
    意思
    0.06
     shores
    0.06
    larında
    0.06
    Act Density 0.003%

    No Known Activations