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

    Neuronpedia

    INDEX
    Explanations

    specific scientific or technical terminology related to comparison and analysis

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

    introduces specific concepts or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    red
    -0.33
    REP
    -0.32
    <?
    -0.32
    rest
    -0.31
    rep
    -0.31
    ide
    -0.30
    must
    -0.29
    lle
    -0.27
     must
    -0.27
    ////////////////
    -0.27
    POSITIVE LOGITS
     propOrder
    0.85
     $_(
    0.73
    IUrlHelper
    0.72
     nakalista
    0.71
    AddAttribute
    0.68
     pleaſure
    0.67
    getMinutes
    0.67
     パンチラ
    0.66
    <unused52>
    0.66
    <unused41>
    0.66
    Act Density 2.387%

    No Known Activations