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

    Neuronpedia

    INDEX
    Explanations

    comma followed by word

    np_acts-logits-general · gemini-2.5-flash-lite

    originally or initially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र
    0.61
    ن
    0.57
    न
    0.57
    3
    0.56
    ำ
    0.56
    á
    0.55
    า
    0.54
    ัง
    0.51
    ll
    0.50
    ी
    0.50
    POSITIVE LOGITS
    ও
    0.54
    p
    0.53
    etzung
    0.52
     اين
    0.50
    podob
    0.50
    도
    0.49
    も
    0.49
     جي
    0.48
     gleaming
    0.48
    혔
    0.47
    Act Density 0.000%

    No Known Activations