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

    Neuronpedia

    INDEX
    Explanations

    French quotations and dialogue references

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

    French words and phrases

    np_acts-logits-general · gemini-2.0-flash

    tech or operating system configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nôtre
    -1.10
     réfrig
    -1.06
     avoient
    -1.05
     dévelo
    -1.03
     feroit
    -1.00
     peindre
    -0.99
     enfans
    -0.97
     élas
    -0.97
     réfugi
    -0.97
     vôtre
    -0.97
    POSITIVE LOGITS
    Portail
    0.74
     Mahomet
    0.56
    homonymie
    0.55
    itinéraire
    0.51
     Pythag
    0.50
     Bayard
    0.50
    évaluateur
    0.49
     Çünkü
    0.48
     Whigs
    0.48
     MiG
    0.47
    Act Density 0.118%

    No Known Activations