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

    Neuronpedia

    INDEX
    Explanations

    the + specific noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.96
    :
    0.54
     The
    0.50
    行う
    0.46
    两大
    0.46
    两
    0.46
    ;
    0.46
    -
    0.46
    ↵↵
    0.45
    }.
    0.45
    POSITIVE LOGITS
    ă
    0.62
    á
    0.59
    ä
    0.57
    ą
    0.56
     waktu
    0.55
    د
    0.55
     diámetro
    0.55
    サイズ
    0.54
     anderes
    0.53
    ok
    0.52
    Act Density 0.709%

    No Known Activations