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

    Neuronpedia

    INDEX
    Explanations

    JSON structure keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䟺
    0.63
    峎
    0.62
    が得
    0.61
    Ꮂ
    0.61
    仠
    0.61
    මි
    0.60
    恴
    0.60
    溶液
    0.59
    тке
    0.59
    体力
    0.59
    POSITIVE LOGITS
    2
    0.75
     and
    0.75
    1
    0.75
     about
    0.70
     that
    0.69
     between
    0.68
     cloned
    0.68
     were
    0.64
    to
    0.63
     YMCA
    0.63
    Act Density 0.086%

    No Known Activations