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

    Neuronpedia

    INDEX
    Explanations

    https URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estudi
    0.35
    𒌆
    0.35
    ائض
    0.34
     discurso
    0.34
     causas
    0.33
    考核
    0.33
     decisões
    0.33
     funções
    0.32
     заявление
    0.32
     expressões
    0.32
    POSITIVE LOGITS
     i
    0.36
    ky
    0.36
    URL
    0.36
     u
    0.36
     Pebble
    0.34
    im
    0.34
     GitHub
    0.33
    他
    0.33
     Google
    0.33
     Hulu
    0.33
    Act Density 0.161%

    No Known Activations