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

    Neuronpedia

    INDEX
    Explanations

    following words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Каждый
    0.42
     Rowling
    0.41
     मोटरसाइकिल
    0.41
     raped
    0.41
    করিয়া
    0.40
     ग्ला
    0.40
    тбол
    0.39
     Estadística
    0.39
     इसमें
    0.38
    वासी
    0.38
    POSITIVE LOGITS
     magyar
    0.45
    om
    0.45
    mag
    0.43
    init
    0.43
     juh
    0.42
    gu
    0.42
     gu
    0.41
    att
    0.41
    gram
    0.40
    aux
    0.40
    Act Density 0.000%

    No Known Activations