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

    Neuronpedia

    INDEX
    Explanations

    .com suffix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ніза
    0.47
    LocalDateTime
    0.43
    Southeast
    0.41
    現在
    0.40
    CommonAncestor
    0.40
    Estab
    0.40
    ньо
    0.40
    Campe
    0.40
    有力
    0.39
    ті
    0.39
    POSITIVE LOGITS
     typeof
    0.48
     jika
    0.47
     v
    0.46
     atau
    0.46
     loại
    0.46
     except
    0.45
     stretchy
    0.44
     chunky
    0.44
     aka
    0.44
     beserta
    0.44
    Act Density 0.007%

    No Known Activations