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

    Neuronpedia

    INDEX
    Explanations

    sentences that express beliefs, assumptions, or hypotheses

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

    would expect or should happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.63
    ftagPool
    -0.63
    rungsseite
    -0.62
    expandindo
    -0.58
    +#+#
    -0.56
    MigrationBuilder
    -0.54
    /**
    -0.54
    transQ
    -0.53
     препратки
    -0.52
     saites
    -0.51
    POSITIVE LOGITS
    should
    0.41
    VAC
    0.40
    Shouldn
    0.40
    harusnya
    0.39
     Ideally
    0.39
     Surely
    0.37
    XCT
    0.37
    expectedResult
    0.37
     normalement
    0.36
     soñ
    0.36
    Act Density 0.354%

    No Known Activations