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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs and related phrases

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

    reporting findings or strikes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coupable
    -0.35
     soldado
    -0.33
    <h1>
    -0.32
    udahkan
    -0.30
    mampuan
    -0.30
     đó
    -0.30
     ifade
    -0.30
     yapan
    -0.29
     varsa
    -0.29
    hidupan
    -0.28
    POSITIVE LOGITS
     EconPapers
    0.68
    AnchorStyles
    0.59
     iconLine
    0.59
    AddTagHelper
    0.59
     MainAxisSize
    0.56
    centralwidget
    0.55
    RTSC
    0.54
     '\\;'
    0.54
    DockStyle
    0.54
    rrggbb
    0.54
    Act Density 0.003%

    No Known Activations