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

    Neuronpedia

    INDEX
    Explanations

    references to legal citations and formal documentation

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

    Followed by "We," "W," "M," or "The."

    np_acts-logits-general · gemini-2.0-flash

    [T]he

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.89
    Geplaatst
    -0.88
    MLLoader
    -0.83
     HasFactory
    -0.80
     CreateTagHelper
    -0.77
    GOTREF
    -0.75
     unknownFields
    -0.75
    Carriera
    -0.74
    IsMutable
    -0.73
    CloseOperation
    -0.72
    POSITIVE LOGITS
     th
    1.44
     tha
    1.15
     thi
    1.13
    Th
    0.99
    th
    0.99
     t
    0.96
     Th
    0.95
     tho
    0.90
     ther
    0.88
     TH
    0.87
    Act Density 0.368%

    No Known Activations