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

    Neuronpedia

    INDEX
    Explanations

    two followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.93
    s
    0.77
    re
    0.77
    i
    0.74
    is
    0.64
    dür
    0.64
     sını
    0.63
     rů
    0.63
     erken
    0.62
    ra
    0.61
    POSITIVE LOGITS
    ва
    0.68
    к
    0.64
    ort
    0.63
    н
    0.63
    ara
    0.60
    ä
    0.60
    в
    0.59
    你
    0.59
    ain
    0.58
    ும்
    0.57
    Act Density 0.327%

    No Known Activations