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

    Neuronpedia

    INDEX
    Explanations

    quantities or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تاکہ
    0.55
     ताकि
    0.54
    :
    0.54
    /#{
    0.52
     contextual
    0.52
    เพื่อ
    0.50
    $-$
    0.49
    [],
    0.49
    ։
    0.49
     ולא
    0.47
    POSITIVE LOGITS
     can
    0.77
     può
    0.73
     possono
    0.72
     are
    0.71
     можуть
    0.71
     είναι
    0.68
     mempunyai
    0.63
     cannot
    0.63
     peuvent
    0.62
     may
    0.62
    Act Density 0.019%

    No Known Activations