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

    Neuronpedia

    INDEX
    Explanations

    references to assistance and support services for individuals in need

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

    support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eletrônico
    -0.57
    <bos>
    -0.57
    MILLISECONDS
    -0.49
     namorado
    -0.49
     cewek
    -0.48
     miglia
    -0.47
     sereia
    -0.46
     dozen
    -0.44
    <h6>
    -0.44
    <em>
    -0.43
    POSITIVE LOGITS
     Support
    1.09
    support
    1.09
     support
    1.08
    Support
    1.05
     SUPPORT
    0.96
    SUPPORT
    0.95
    upport
    0.91
     suppor
    0.90
     supports
    0.89
     suport
    0.85
    Act Density 0.033%

    No Known Activations