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

    Neuronpedia

    INDEX
    Explanations

    knew what, distinct from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    omot
    0.49
    Lus
    0.47
    ክምና
    0.46
     covariates
    0.46
    measures
    0.45
    меры
    0.44
     جیل
    0.44
    ዢ
    0.44
    Bradley
    0.43
     கேட்டு
    0.43
    POSITIVE LOGITS
     for
    0.59
     and
    0.55
     organisers
    0.54
     (
    0.52
     página
    0.50
     größte
    0.50
     Festival
    0.50
     AND
    0.49
     danza
    0.49
    la
    0.49
    Act Density 0.000%

    No Known Activations