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

    Neuronpedia

    INDEX
    Explanations

    statements regarding existence and identity

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

    is or was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    matchCondition
    -0.56
    AccessorTable
    -0.49
    =$?
    -0.47
     فريبيس
    -0.46
     виправивши
    -0.46
     bezeichneter
    -0.45
    InstrumentedTest
    -0.45
     pinulongan
    -0.44
    SBATCH
    -0.44
    出版年
    -0.44
    POSITIVE LOGITS
     essential
    0.47
     important
    0.46
     truly
    0.44
    divarius
    0.43
     crucial
    0.42
     vital
    0.42
     is
    0.42
     one
    0.41
     integral
    0.41
    是
    0.40
    Act Density 0.037%

    No Known Activations