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

    Neuronpedia

    INDEX
    Explanations

    elements related to political discourse and societal divides

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

    preceding conjunctions or commas

    np_acts-logits-general · gemini-2.0-flash

    consequences or alternative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.68
    titleMargin
    -0.66
     requieren
    -0.65
    deleteById
    -0.62
     nécess
    -0.59
    TintMode
    -0.58
     devront
    -0.57
    pherals
    -0.57
     sanitaires
    -0.57
     devaient
    -0.57
    POSITIVE LOGITS
     maka
    0.70
     you
    0.69
     youll
    0.69
    就不会
    0.64
     will
    0.60
     everything
    0.59
     sẽ
    0.58
     we
    0.57
     chances
    0.56
    就能
    0.55
    Act Density 0.368%

    No Known Activations