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

    Neuronpedia

    INDEX
    Explanations

    multi-script language detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GPUs
    0.47
    GraphQL
    0.46
     Poker
    0.46
    Gener
    0.46
    Story
    0.46
    Kingdom
    0.46
     aparel
    0.44
     magia
    0.44
    Zombie
    0.44
    Code
    0.43
    POSITIVE LOGITS
    нави
    0.47
    ִ
    0.46
    ulation
    0.44
    できます
    0.43
    हत
    0.43
    ଭ
    0.43
     pursued
    0.42
     СССР
    0.42
    vori
    0.41
    払
    0.41
    Act Density 0.109%

    No Known Activations