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

    Neuronpedia

    INDEX
    Explanations

    numeric comparisons and thresholds

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

    numerical thresholds and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.44
    providedIn
    -0.39
    FormTagHelper
    -0.38
    ComponentName
    -0.38
     volna
    -0.38
     oreille
    -0.38
     desem
    -0.37
     demurrer
    -0.37
     BoxDecoration
    -0.36
    นี่
    -0.36
    POSITIVE LOGITS
    期刊论文
    0.61
     (>
    0.61
     $<
    0.61
     $>
    0.59
     ≥
    0.54
    выше
    0.54
    Beyond
    0.52
    geq
    0.52
    超過
    0.52
     exceeding
    0.51
    Act Density 0.087%

    No Known Activations