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

    Neuronpedia

    INDEX
    Explanations

    look around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Paying
    0.42
    for
    0.41
    关键词
    0.40
    kung
    0.39
     Elabor
    0.39
    oruč
    0.39
    復
    0.39
    ValuePair
    0.38
    átu
    0.38
     různých
    0.38
    POSITIVE LOGITS
     pointed
    0.50
    erdas
    0.47
    ຕາມ
    0.46
    라는
    0.45
     permitido
    0.44
    ார்கள்
    0.44
     অভিভাবকদের
    0.44
    町村
    0.43
     promoters
    0.42
     dispositif
    0.42
    Act Density 0.002%

    No Known Activations