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

    Neuronpedia

    INDEX
    Explanations

    specific formatting markers and symbols used in mathematical expressions

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

    Image or figure file paths and extensions

    np_acts-logits-general · gemini-2.0-flash

    width specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    -0.67
    ReusableCell
    -0.52
     zu
    -0.50
     to
    -0.47
     and
    -0.46
    Auswahl
    -0.46
    дарь
    -0.46
    er
    -0.46
     ad
    -0.46
    principalTable
    -0.45
    POSITIVE LOGITS
     ſmall
    0.82
    amaño
    0.82
     <>",
    0.75
     Sandstone
    0.74
     cref
    0.74
     holotype
    0.73
    =\
    0.73
     Synagogue
    0.71
    esserts
    0.71
     ſt
    0.71
    Act Density 0.059%

    No Known Activations