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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	make
    -0.07
     Funktion
    -0.06
     memory
    -0.06
    ักด
    -0.06
     Delegate
    -0.06
     Strings
    -0.06
     spoken
    -0.06
    oj
    -0.06
    apiro
    -0.06
     ků
    -0.06
    POSITIVE LOGITS
     cry
    0.07
    ,!
    0.07
     chiropr
    0.07
     Scheduled
    0.07
     Romance
    0.07
     brib
    0.07
    按
    0.06
     Совет
    0.06
     ار
    0.06
    弋
    0.06
    Act Density 0.001%

    No Known Activations