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

    Neuronpedia

    INDEX
    Explanations

    linguistic terms related to grammar and case morphology

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

    case forms and plurals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schre
    -0.32
     Pfe
    -0.30
     another
    -0.30
     Far
    -0.30
     fra
    -0.29
     варто
    -0.28
    -
    -0.28
     đầu
    -0.28
     COUR
    -0.28
     blue
    -0.27
    POSITIVE LOGITS
    AccessorTable
    0.79
    tagHelperRunner
    0.73
    AndEndTag
    0.72
    MLLoader
    0.71
     pleaſure
    0.70
     Normdatei
    0.70
     leaſt
    0.68
     myſelf
    0.66
    ंदीखरीदारी
    0.66
     queſta
    0.66
    Act Density 0.051%

    No Known Activations