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

    Neuronpedia

    INDEX
    Explanations

    logical triggers that indicate sequential actions or processes

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

    Followed by "you," "the," "these," or "a."

    np_acts-logits-general · gemini-2.0-flash

    completion of a condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.72
     pinulongan
    -0.68
     autrement
    -0.55
    SuspendLayout
    -0.52
    HasColumnName
    -0.50
    adpleegd
    -0.50
     justru
    -0.49
     ведь
    -0.49
     marcher
    -0.48
     malah
    -0.48
    POSITIVE LOGITS
     xong
    0.74
     successfully
    0.62
     sufficiently
    0.60
    IsMutable
    0.59
     satisfactorily
    0.58
     stabili
    0.58
     satisfactory
    0.58
    successfully
    0.57
     stabilize
    0.57
     selesai
    0.56
    Act Density 0.274%

    No Known Activations