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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation and graphical elements in text

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

    kind of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.64
    SourceChecksum
    -0.62
    GraphicsUnit
    -0.58
    ValueGeneration
    -0.56
     CascadeType
    -0.55
    RegressionTest
    -0.54
     Signalez
    -0.54
     pinulongan
    -0.54
     iconLine
    -0.54
    errHandler
    -0.52
    POSITIVE LOGITS
     surla
    0.36
    Karriere
    0.32
    наче
    0.32
    versies
    0.32
     deber
    0.32
    ся
    0.32
     במק
    0.31
     Etwas
    0.31
    callee
    0.31
     hoạch
    0.31
    Act Density 0.253%

    No Known Activations