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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions and emotions

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

    pronoun followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.85
     שוליים
    -0.80
    Personensuche
    -0.79
     ब्रेकडाउन
    -0.78
    GEBURTSDATUM
    -0.77
     Мексичка
    -0.73
     Administrativna
    -0.72
    сылкі
    -0.68
    ValueStyle
    -0.68
    -0.66
    POSITIVE LOGITS
     H
    0.35
    classmethod
    0.35
     perfect
    0.35
     Arnold
    0.30
     ocup
    0.30
     ajudá
    0.30
     recommend
    0.30
    wäh
    0.29
    showMessage
    0.29
     Fä
    0.28
    Act Density 0.004%

    No Known Activations