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

    Neuronpedia

    INDEX
    Explanations

    various punctuation marks, particularly slashes and periods

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

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    portál
    -0.49
    angliski
    -0.47
    ſelves
    -0.45
     ympä
    -0.44
     egenskaper
    -0.43
    andExpect
    -0.43
    AndEndTag
    -0.43
     judíos
    -0.42
    ModelSerializer
    -0.42
     demas
    -0.42
    POSITIVE LOGITS
    +#+
    0.54
     AssemblyCompany
    0.50
     Wallis
    0.47
    import
    0.44
    bitan
    0.42
    ophageal
    0.41
     Colin
    0.40
     Euro
    0.40
    ostock
    0.40
    <?
    0.39
    Act Density 0.001%

    No Known Activations