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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical or programming issues

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

    French words and phrases

    np_acts-logits-general · gemini-2.0-flash

    un/une + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -1.19
     greateſt
    -1.15
     houſe
    -1.15
     ſmall
    -1.14
     pleaſure
    -1.13
     Houſe
    -1.10
     Majefty
    -1.10
     ſtate
    -1.09
     purpoſe
    -1.09
     Monfieur
    -1.08
    POSITIVE LOGITS
     due
    0.41
     re
    0.40
     
    0.40
     co
    0.37
     v
    0.35
     hit
    0.34
     be
    0.34
     genannt
    0.34
    voix
    0.33
     rode
    0.32
    Act Density 0.072%

    No Known Activations