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

    Neuronpedia

    INDEX
    Explanations

    closing HTML tags and their associated attributes

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

    XML and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.75
    aarrggbb
    -0.59
     Numerade
    -0.59
    ftagPool
    -0.57
    ConstraintMaker
    -0.56
    الدراسه
    -0.53
    angeran
    -0.53
     nahilalakip
    -0.52
    談社
    -0.52
    makeText
    -0.52
    POSITIVE LOGITS
     griechischen
    0.43
     allgemeine
    0.40
     państw
    0.40
    SpringBootTest
    0.39
     nowo
    0.39
     Erwartungen
    0.39
     działal
    0.38
     AssemblyCulture
    0.38
    voerd
    0.37
     entera
    0.36
    Act Density 0.302%

    No Known Activations