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

    Neuronpedia

    INDEX
    Explanations

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     néanmoins
    1.63
     presentaciones
    1.59
     supplémentaires
    1.56
    თან
    1.55
     isomorphisms
    1.55
    𝐀
    1.55
    ᙱ
    1.55
     linhas
    1.53
     불구하고
    1.53
    を果た
    1.52
    POSITIVE LOGITS
    ry
    1.97
    ing
    1.84
    ial
    1.73
    ?
    1.68
    ina
    1.67
    ro
    1.66
    ating
    1.55
    izing
    1.51
    :
    1.48
    isms
    1.47
    Act Density 0.002%

    No Known Activations