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

    Neuronpedia

    INDEX
    Explanations

    arg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etat
    -0.07
     coverage
    -0.07
     performances
    -0.07
    ackson
    -0.07
     funkce
    -0.06
    REEN
    -0.06
    ीट
    -0.06
    pent
    -0.06
    tea
    -0.06
    ويل
    -0.06
    POSITIVE LOGITS
     arg
    0.14
     Arg
    0.12
    Arg
    0.11
    arg
    0.10
    (arg
    0.09
    	arg
    0.09
    ARG
    0.09
     ARG
    0.08
    Marg
    0.08
     Alg
    0.08
    Act Density 0.009%

    No Known Activations