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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diversos
    -0.06
     یعنی
    -0.06
    иты
    -0.06
     mucho
    -0.06
     yarar
    -0.06
     Wikispecies
    -0.06
    -four
    -0.06
    şt
    -0.06
     Yeni
    -0.06
     stamina
    -0.06
    POSITIVE LOGITS
     auf
    0.07
     climax
    0.07
     vel
    0.07
     UP
    0.07
     urlencode
    0.07
    ンフ
    0.07
    .Down
    0.07
     орг
    0.06
    .fs
    0.06
     Brah
    0.06
    Act Density 0.006%

    No Known Activations