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

    Neuronpedia

    INDEX
    Explanations

    toy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.86
    to
    0.80
    ف
    0.80
    the
    0.77
    。
    0.72
    a
    0.67
    ad
    0.66
    folio
    0.64
     is
    0.64
    aal
    0.63
    POSITIVE LOGITS
     juguetes
    0.74
     Arbeit
    0.71
    v
    0.71
     dolls
    0.70
    বেক
    0.69
     toys
    0.67
     doll
    0.66
     ﺍ
    0.66
     Akademii
    0.66
     Apare
    0.66
    Act Density 0.004%

    No Known Activations