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

    Neuronpedia

    INDEX
    Explanations

    technical terms and specifications related to engineering and development processes

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

    ending in "s"

    np_acts-logits-general · gemini-2.0-flash

    profiles and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.65
     pleaſure
    -0.62
    GEBURTS
    -0.59
    MLLoader
    -0.58
     purpoſe
    -0.56
    nologue
    -0.55
     ſta
    -0.54
     ActivatedRoute
    -0.52
     vœux
    -0.52
    ulemon
    -0.52
    POSITIVE LOGITS
     neler
    0.74
     jotka
    0.69
    capes
    0.63
    icles
    0.61
     leerlingen
    0.60
    SCs
    0.59
     denen
    0.59
    hirts
    0.58
     אלה
    0.58
    copes
    0.57
    Act Density 3.597%

    No Known Activations