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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and code syntax within a document

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

    Code, table, or reference-like syntax

    np_acts-logits-general · gemini-2.0-flash

    HTML/academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     super
    -0.55
    Chham
    -0.48
     fast
    -0.47
     Sand
    -0.45
    ്യ
    -0.45
     Maker
    -0.45
     the
    -0.45
     San
    -0.44
    rav
    -0.44
     future
    -0.44
    POSITIVE LOGITS
     kasarigan
    0.93
    endphp
    0.88
     snippetHide
    0.87
     المعيارى
    0.80
     disambiguazione
    0.79
     tartalomajánló
    0.76
     firebaseConfig
    0.72
    ❋
    0.72
    _))
    0.71
    ]")]
    0.71
    Act Density 0.140%

    No Known Activations