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

    Neuronpedia

    INDEX
    Explanations

    specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Russia
    0.54
     வழிப
    0.50
    Wind
    0.48
    VIA
    0.48
     спа
    0.48
    но
    0.47
     другой
    0.47
    BREAK
    0.47
     усилия
    0.47
    स्प
    0.46
    POSITIVE LOGITS
    ened
    0.41
    是对
    0.40
     tov
    0.40
     dovr
    0.40
     labs
    0.40
    orys
    0.40
     tiss
    0.39
    kne
    0.39
     όπου
    0.39
    是谁
    0.39
    Act Density 0.001%

    No Known Activations