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

    Neuronpedia

    INDEX
    Explanations

    showing awareness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    चलित
    0.49
     संपर्क
    0.47
     シンプル
    0.46
    upcoming
    0.46
    cią
    0.46
    輸出
    0.46
    ರ್
    0.44
    いつ
    0.44
    無
    0.44
    落地
    0.44
    POSITIVE LOGITS
     differing
    0.49
     atténuées
    0.47
     beer
    0.46
     ૩
    0.45
     costes
    0.44
     enanti
    0.44
     positrons
    0.44
     copol
    0.43
     vissa
    0.43
     predomin
    0.43
    Act Density 0.008%

    No Known Activations