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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical concepts, particularly in the context of non-Gaussian distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "non" or foreign language text

    np_acts-logits-general · gemini-2.0-flash

    non-start of negations or specific prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mybatisplus
    -0.55
     Commencez
    -0.53
     invokingState
    -0.51
     prochains
    -0.50
    :✨
    -0.48
     fueran
    -0.47
    "");
    -0.46
    beforeAll
    -0.45
    tagext
    -0.44
     igjen
    -0.44
    POSITIVE LOGITS
     è
    1.10
     si
    1.04
     ha
    0.96
     viene
    0.87
    IsContent
    0.84
    twimg
    0.77
     era
    0.74
     può
    0.72
     είναι
    0.70
     έχει
    0.67
    Act Density 0.017%

    No Known Activations