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

    Neuronpedia

    INDEX
    Explanations

    notable or exceptional qualities in descriptions or observations

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

    striking features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelves
    -0.56
     poffible
    -0.48
     theſe
    -0.45
    ſand
    -0.44
     Majefty
    -0.44
     Jefus
    -0.43
     Chriftian
    -0.41
     ſch
    -0.41
     ſeveral
    -0.41
     Houſe
    -0.41
    POSITIVE LOGITS
    InitVars
    0.59
     الحره
    0.53
    ">//
    0.52
    tagext
    0.50
    farwyddwr
    0.50
     noticed
    0.49
     conspicuous
    0.48
    تقاوى
    0.48
    InjectAttribute
    0.48
    noticed
    0.48
    Act Density 0.183%

    No Known Activations