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

    Neuronpedia

    INDEX
    Explanations

    little high, little low

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.61
    ли
    0.53
    ën
    0.49
    ls
    0.47
     encontramos
    0.47
    ität
    0.46
    рование
    0.46
    nh
    0.46
    packing
    0.45
    panel
    0.45
    POSITIVE LOGITS
     식으로
    0.55
    ്യ
    0.53
     Αν
    0.53
     Elektr
    0.53
     ዓይነት
    0.53
    帏
    0.52
     Nutr
    0.52
     Ano
    0.50
     ทด
    0.50
    Jeg
    0.50
    Act Density 0.000%

    No Known Activations