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

    Neuronpedia

    INDEX
    Explanations

    hardware components and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    お
    0.85
    お客
    0.80
     bebas
    0.76
    いい
    0.73
     pemilihan
    0.71
     kesulitan
    0.70
    のである
    0.69
    ukary
    0.69
     negara
    0.68
    ų
    0.68
    POSITIVE LOGITS
     a
    1.37
    ే
    1.18
    ة
    1.16
    。
    1.08
    ал
    1.00
     ribbons
    0.98
    ي
    0.95
    다
    0.94
     ribbon
    0.92
    ва
    0.91
    Act Density 0.009%

    No Known Activations