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

    Neuronpedia

    INDEX
    Explanations

    #include

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	fmt
    -0.07
     gun
    -0.07
    ltk
    -0.07
     covered
    -0.06
    ук
    -0.06
     згад
    -0.06
     segundo
    -0.06
     decides
    -0.06
    ΗΤ
    -0.06
     nostr
    -0.06
    POSITIVE LOGITS
    _work
    0.07
     fatalError
    0.07
     displaced
    0.06
     виконання
    0.06
    范
    0.06
     Hindered
    0.06
     Broadcasting
    0.06
    orage
    0.06
    dration
    0.06
     Physiology
    0.06
    Act Density 0.016%

    No Known Activations