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

    Neuronpedia

    INDEX
    Explanations

    .com URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paed
    0.80
     সভায়
    0.78
    uição
    0.77
     திருச்சி
    0.77
    чната
    0.75
     सीजी
    0.75
    ιάς
    0.75
    TextMesh
    0.75
     აღმასრულ
    0.74
    owego
    0.74
    POSITIVE LOGITS
    ?
    0.80
     comes
    0.73
     consider
    0.71
    com
    0.67
     come
    0.66
    나
    0.64
    !
    0.64
     arsenal
    0.62
    orm
    0.61
    Come
    0.61
    Act Density 0.027%

    No Known Activations