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

    Neuronpedia

    INDEX
    Explanations

    phrases signaling judgment or evaluation

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

    determiners followed by abstract nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.51
    expandindo
    -0.38
     <",
    -0.38
    AnimationsModule
    -0.37
     préfé
    -0.34
     Préférences
    -0.34
     Bands
    -0.34
     przys
    -0.32
     dAtA
    -0.32
     Formulation
    -0.30
    POSITIVE LOGITS
    richTextPanel
    0.64
    scryfall
    0.52
     Italijanski
    0.50
    0.49
     HasFactory
    0.48
    QMetaType
    0.48
    msgTypes
    0.47
    vix
    0.47
    Handlung
    0.46
     nakalista
    0.45
    Act Density 0.035%

    No Known Activations