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

    Neuronpedia

    INDEX
    Explanations

    instances of strong emotional expressions and related questioning

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

    what can be said

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lorette
    -0.61
     CreateTagHelper
    -0.57
    Zeneca
    -0.52
    localctx
    -0.52
    دانشنامهٔ
    -0.50
     دیکھیے
    -0.47
    íncia
    -0.47
     ujednoznacz
    -0.47
    errHandler
    -0.46
     שוליים
    -0.46
    POSITIVE LOGITS
    ്ട
    0.32
    打ち
    0.31
    resizingMask
    0.30
     onCreateView
    0.30
    mişti
    0.30
    dataTable
    0.29
    ModelAdmin
    0.29
     early
    0.28
     invasion
    0.28
    usermodel
    0.28
    Act Density 0.062%

    No Known Activations