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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating claims, denials, and reports related to actions or events

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

    last month, late August

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.58
    tvguidetime
    -0.54
     defaultstate
    -0.53
    ArgsConstructor
    -0.51
    ReusableCell
    -0.51
    ronpa
    -0.48
    ThroughAttribute
    -0.40
     betweenstory
    -0.39
    ContentLoaded
    -0.39
     Photocase
    -0.39
    POSITIVE LOGITS
     ivelany
    0.51
     cum
    0.43
     للاسماء
    0.42
    &__
    0.41
     prompted
    0.41
     <<<<<<<<<<<<<<
    0.41
     largely
    0.40
     led
    0.40
     الحره
    0.40
     Италијани
    0.40
    Act Density 0.319%

    No Known Activations