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

    Neuronpedia

    INDEX
    Explanations

    talking about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    underland
    0.44
     criaturas
    0.43
     તમને
    0.43
     interesados
    0.42
     interesado
    0.41
    grapes
    0.40
    zim
    0.40
     certo
    0.40
    oney
    0.39
    itarian
    0.39
    POSITIVE LOGITS
     되는
    0.45
     す
    0.43
    鹄
    0.41
     повністю
    0.41
     正
    0.41
     رکھنے
    0.41
     внутріш
    0.41
     건물
    0.41
    ทั้งหมด
    0.40
     가운데
    0.40
    Act Density 0.003%

    No Known Activations