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

    Neuronpedia

    INDEX
    Explanations

    instances and variations of content management and publishing

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

    scripts and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Scales
    -0.36
    jsii
    -0.35
    ibatis
    -0.34
     Standardization
    -0.33
     referenties
    -0.33
     nurse
    -0.33
     glaucoma
    -0.33
     Transplantation
    -0.33
     tips
    -0.33
     NoSuch
    -0.32
    POSITIVE LOGITS
    Personensuche
    0.66
     فريبيس
    0.62
    ymce
    0.57
    SourceChecksum
    0.54
    хьтан
    0.50
     مشين
    0.50
     виправивши
    0.48
     OMITBAD
    0.47
    nezeu
    0.47
    +#+
    0.46
    Act Density 0.013%

    No Known Activations