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

    Neuronpedia

    INDEX
    Explanations

    small

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    らく
    -0.07
     επα
    -0.06
     (++
    -0.06
     предназнач
    -0.06
    endet
    -0.06
     kararı
    -0.06
    κα
    -0.06
    .Concat
    -0.06
    specialchars
    -0.06
    اشته
    -0.06
    POSITIVE LOGITS
     kry
    0.08
     Other
    0.07
     affiliated
    0.07
     Expect
    0.07
    venile
    0.07
    	password
    0.07
     comparisons
    0.07
     specialist
    0.07
     вий
    0.06
     …
    0.06
    Act Density 0.006%

    No Known Activations