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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    การ
    0.84
    ການ
    0.80
     Use
    0.79
     Pra
    0.79
     Cells
    0.75
     Prior
    0.74
    田
    0.74
    ALLY
    0.74
    ing
    0.73
    ally
    0.73
    POSITIVE LOGITS
     који
    1.56
     dando
    1.21
     evitando
    1.19
     koji
    1.18
    😧
    1.17
     mostrando
    1.16
     který
    1.15
     ktorý
    1.15
     seinen
    1.14
     amethyst
    1.13
    Act Density 0.204%

    No Known Activations