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

    Neuronpedia

    INDEX
    Explanations

    references to support or assistance in various contexts

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

    "support"

    np_acts-logits-general · gemini-2.0-flash

    support for future, transmission, requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.52
     eletrônico
    -0.47
    MILLISECONDS
    -0.44
     casó
    -0.41
    catraz
    -0.40
     cewek
    -0.40
    CastException
    -0.40
     namorado
    -0.38
     miglia
    -0.38
     lucru
    -0.38
    POSITIVE LOGITS
     Support
    1.28
     support
    1.28
    support
    1.26
    Support
    1.23
     SUPPORT
    1.15
    SUPPORT
    1.11
     suppor
    1.10
     supports
    1.09
    upport
    1.09
     Supports
    1.02
    Act Density 0.125%

    No Known Activations