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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and interactions

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

    French text and interjections

    np_acts-logits-general · gemini-2.0-flash

    voir, cool, dommage, oui, chance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.64
     prisonniers
    -0.63
    antaranya
    -0.63
    Datuak
    -0.62
     spalle
    -0.61
     devront
    -0.61
     tevens
    -0.61
     condamné
    -0.60
     acesta
    -0.60
     mêmes
    -0.60
    POSITIVE LOGITS
     something
    0.57
     nice
    0.57
    !
    0.57
    glPushMatrix
    0.56
     cái
    0.52
     loads
    0.51
     I
    0.50
    kirchen
    0.50
     haha
    0.50
     stuff
    0.49
    Act Density 0.253%

    No Known Activations