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

    Neuronpedia

    INDEX
    Explanations

    say [number 9]

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aloud
    -0.06
     Sparks
    -0.06
    iterations
    -0.06
    	module
    -0.06
     Они
    -0.06
    Block
    -0.06
    abolic
    -0.06
     lst
    -0.06
    λογ
    -0.06
     Gould
    -0.06
    POSITIVE LOGITS
     yüzden
    0.07
     мень
    0.07
     прож
    0.07
     那
    0.07
     années
    0.06
     khăn
    0.06
     अद
    0.06
     pocket
    0.06
     yazı
    0.06
    -connected
    0.06
    Act Density 0.037%

    No Known Activations