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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns/brand names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     też
    -0.07
     hoki
    -0.07
     importantly
    -0.07
     uses
    -0.07
     vag
    -0.07
     če
    -0.07
     których
    -0.07
    куда
    -0.07
     fugir
    -0.07
     whom
    -0.07
    POSITIVE LOGITS
    =count
    0.08
    ,re
    0.08
    يدي
    0.08
     artisan
    0.07
     Timber
    0.07
     timber
    0.07
     Domin
    0.07
     mentorship
    0.07
    imente
    0.07
    omega
    0.07
    Act Density 0.758%

    No Known Activations