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

    Neuronpedia

    INDEX
    Explanations

    the noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    కు
    0.55
    ，
    0.54
    рока
    0.50
    뎐
    0.50
    αιν
    0.50
    ،
    0.48
    αν
    0.47
    ри
    0.47
    рии
    0.47
     namani
    0.46
    POSITIVE LOGITS
     to
    0.70
     are
    0.63
     są
    0.58
     at
    0.57
     sono
    0.54
     was
    0.53
    ată
    0.52
     são
    0.52
     gustaría
    0.52
     be
    0.52
    Act Density 0.055%

    No Known Activations