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

    Neuronpedia

    INDEX
    Explanations

    references to interpretation and analysis, particularly in religious or philosophical contexts

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

    interpretation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    saraba
    -0.46
     BoxDecoration
    -0.44
    featureID
    -0.41
     typelib
    -0.41
    AddTagHelper
    -0.41
    conomie
    -0.41
    setVerticalGroup
    -0.40
    ClientSize
    -0.40
    ConstraintMaker
    -0.39
    ſchen
    -0.39
    POSITIVE LOGITS
     interpretation
    0.71
     interpretations
    0.66
     interpreta
    0.61
     interpretación
    0.60
    interpretation
    0.57
    interprétation
    0.56
     interpretar
    0.55
     interpre
    0.55
     interpretive
    0.55
     interpret
    0.54
    Act Density 0.037%

    No Known Activations