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

    Neuronpedia

    INDEX
    Explanations

    structured data elements and their attributes in text

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

    Code-related commands/functions

    np_acts-logits-general · gemini-2.0-flash

    parameter name assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     again
    -0.39
     else
    -0.36
     also
    -0.35
    else
    -0.35
    appliquent
    -0.35
     yet
    -0.34
     otherwise
    -0.32
    ISODE
    -0.31
    ยิ่ง
    -0.30
    again
    -0.30
    POSITIVE LOGITS
     cherchés
    0.77
    SourceChecksum
    0.75
    intios
    0.57
    fjspx
    0.57
    معلومات
    0.55
     ModelExpression
    0.53
    findViewById
    0.49
    GIVEREF
    0.49
    InlineData
    0.49
     ModelRenderer
    0.49
    Act Density 0.815%

    No Known Activations