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

    Neuronpedia

    INDEX
    Explanations

    calculations and verification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (||
    -0.08
    -transform
    -0.07
    akin
    -0.07
     essentiellement
    -0.07
     xây
    -0.07
    _build
    -0.07
     akin
    -0.07
    *:
    -0.07
    τερ
    -0.07
    (Add
    -0.07
    POSITIVE LOGITS
     nochmals
    0.12
     novamente
    0.11
    再次
    0.10
     weiterhin
    0.10
     jeszcze
    0.10
     erneut
    0.10
     שוב
    0.10
     nuevamente
    0.09
     nochmal
    0.09
     volled
    0.09
    Act Density 0.076%

    No Known Activations