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

    Neuronpedia

    INDEX
    Explanations

    graphic sexual content and bees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    लि
    0.55
    ilded
    0.50
    glades
    0.49
    دد
    0.47
    ieger
    0.47
    حل
    0.46
    webs
    0.46
    ب
    0.45
    ه
    0.45
    دت
    0.45
    POSITIVE LOGITS
     one
    0.61
     Danube
    0.57
     lamp
    0.56
    ER
    0.55
    UZ
    0.55
    RA
    0.54
     camera
    0.53
     satu
    0.52
    ES
    0.52
    ນາ
    0.52
    Act Density 0.000%

    No Known Activations