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

    Neuronpedia

    INDEX
    Explanations

    language related to decision-making and instinct within a societal context

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

    Subjective or emotional language

    np_acts-logits-general · gemini-2.0-flash

    sentiment, conjecture, or mystery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.78
    ритори
    -0.63
     Inscrivez
    -0.52
     myſelf
    -0.51
     Allein
    -0.51
     Vikipedi
    -0.50
     IndexError
    -0.49
    ModelSerializer
    -0.47
     Everywhere
    -0.47
     fufficient
    -0.46
    POSITIVE LOGITS
     subjective
    1.19
     emotional
    1.14
     intang
    1.09
     intangible
    1.03
     qualitative
    1.01
     Emotional
    0.95
    emotional
    0.94
     emotion
    0.89
     emotions
    0.88
     emocional
    0.86
    Act Density 0.473%

    No Known Activations