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

    Neuronpedia

    INDEX
    Explanations

    structural patterns in formatting elements like punctuation and spacing

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

    Prepositions and conjunctions

    np_acts-logits-general · gemini-2.0-flash

    dates and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.74
     gynhyrchwyd
    -0.68
    GOTREF
    -0.67
    featureID
    -0.65
    EndContext
    -0.64
    onViewCreated
    -0.64
    offsetof
    -0.63
    expandindo
    -0.61
     Chwiliwch
    -0.59
     EClass
    -0.58
    POSITIVE LOGITS
     by
    0.75
    by
    0.73
     oleh
    0.53
     (
    0.52
     devised
    0.52
     Thursday
    0.51
    aka
    0.50
    Description
    0.49
    bewerken
    0.49
     July
    0.48
    Act Density 0.760%

    No Known Activations