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

    Neuronpedia

    INDEX
    Explanations

    G

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thou
    -0.07
     contracts
    -0.07
    fulness
    -0.07
     specified
    -0.07
    	Double
    -0.06
    据
    -0.06
     displaced
    -0.06
    between
    -0.06
     option
    -0.06
    -web
    -0.06
    POSITIVE LOGITS
    ıydı
    0.07
    ients
    0.07
    chandle
    0.07
    �
    0.07
     İlk
    0.06
     vys
    0.06
     heapq
    0.06
    ichni
    0.06
    )p
    0.06
     aile
    0.06
    Act Density 0.009%

    No Known Activations