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

    Neuronpedia

    INDEX
    Explanations

    loss of innocence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وهذا
    0.49
    ណ៌
    0.48
    ITAS
    0.47
     ಹೃದಯ
    0.46
    和服务
    0.46
     Thal
    0.46
     izaz
    0.45
     இதய
    0.45
    ས་
    0.45
    itivos
    0.44
    POSITIVE LOGITS
    ن
    0.60
    ન
    0.56
    ট
    0.55
    ק
    0.50
    م
    0.49
     hvis
    0.49
    خ
    0.48
    мі
    0.48
    ق
    0.48
    ві
    0.47
    Act Density 0.000%

    No Known Activations