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

    Neuronpedia

    INDEX
    Explanations

    say "engine"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quivos
    -0.07
     Ajax
    -0.07
     Hüs
    -0.07
    _ACTIVE
    -0.06
     войны
    -0.06
     Wimbledon
    -0.06
    _BLACK
    -0.06
     [,
    -0.06
    _xt
    -0.06
     Máy
    -0.06
    POSITIVE LOGITS
     juvenile
    0.06
     zvuky
    0.06
    	cfg
    0.06
    visor
    0.06
     AZ
    0.06
    	store
    0.06
    rary
    0.05
    helper
    0.05
    σει
    0.05
    {-
    0.05
    Act Density 0.055%

    No Known Activations