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

    Neuronpedia

    INDEX
    Explanations

    conversational and rhetorical questions

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

    Contractions and auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    auxiliary questions with pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exacts
    -0.67
    jatel
    -0.59
    ніципалі
    -0.56
     الحره
    -0.55
     ddelweddau
    -0.54
    省市镇
    -0.54
    GEBURTSDATUM
    -0.52
    béco
    -0.50
    новништво
    -0.50
     Yourself
    -0.50
    POSITIVE LOGITS
     it
    1.03
     they
    0.93
     она
    0.70
     вона
    0.64
     she
    0.64
     они
    0.63
    它
    0.63
     he
    0.59
     оно
    0.58
     он
    0.55
    Act Density 0.159%

    No Known Activations