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

    Neuronpedia

    INDEX
    Explanations

    domain names with slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ektor
    0.64
     zouden
    0.61
    ates
    0.59
     parku
    0.59
     Huffington
    0.58
     ২০১৫
    0.58
     Valerie
    0.56
     Franti
    0.55
     seuls
    0.55
    l
    0.53
    POSITIVE LOGITS
    🥶
    0.57
     ආහාර
    0.55
     combin
    0.54
    ்க்க
    0.54
     كلام
    0.53
     fruitful
    0.52
     food
    0.52
    win
    0.51
     خدمة
    0.50
     calam
    0.50
    Act Density 0.031%

    No Known Activations