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

    Neuronpedia

    INDEX
    Explanations

    information regarding quantitative assessments and comparisons

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

    "high" or "low" and related words

    np_acts-logits-general · gemini-2.0-flash

    high and low quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.64
    principalTable
    -0.61
     eventdata
    -0.55
     الدولى
    -0.54
    TabStop
    -0.53
    Хьажоргаш
    -0.53
     مرئيه
    -0.52
     ivelany
    -0.52
    abestanden
    -0.52
     Wikimedijinoj
    -0.51
    POSITIVE LOGITS
     high
    3.18
    high
    2.84
     low
    2.81
     higher
    2.76
    High
    2.46
    higher
    2.44
     High
    2.40
     HIGH
    2.36
    HIGH
    2.35
     tinggi
    2.29
    Act Density 0.950%

    No Known Activations