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

    Neuronpedia

    INDEX
    Explanations

    developer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atrib
    -0.07
    ูช
    -0.06
     Altın
    -0.06
     consultancy
    -0.06
     assertions
    -0.06
    kas
    -0.06
     restores
    -0.06
    ी-
    -0.06
    	RTE
    -0.06
    ACES
    -0.06
    POSITIVE LOGITS
    developer
    0.08
     Zombie
    0.07
    ,None
    0.06
    .Val
    0.06
     jeu
    0.06
     situ
    0.06
    lan
    0.06
     intval
    0.06
     신
    0.06
     sup
    0.06
    Act Density 0.001%

    No Known Activations