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

    Neuronpedia

    INDEX
    Explanations

    A followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ende
    0.43
     axiomatic
    0.38
     Петро
    0.38
     benign
    0.37
     leukaemia
    0.37
    benzene
    0.36
     navigating
    0.35
     landowner
    0.35
    Performed
    0.35
     memoria
    0.35
    POSITIVE LOGITS
    rahydro
    0.41
    動物
    0.40
    鞋
    0.40
     whor
    0.39
    ிரு
    0.38
    ிகள்
    0.38
    মুক্ত
    0.38
    󠁷
    0.38
     INTERACTIONS
    0.37
    ologists
    0.37
    Act Density 0.000%

    No Known Activations