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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms that indicate comparisons or contrasts in outcomes and conditions

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

    comparisons and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.73
    -0.61
    Kjelder
    -0.52
     lenker
    -0.51
     kasarigan
    -0.50
    ✨:
    -0.50
    waitKey
    -0.49
    tvguidetime
    -0.47
    addContainerGap
    -0.47
    HideFlags
    -0.46
    POSITIVE LOGITS
    EndContext
    0.39
    tonsoft
    0.38
     gốc
    0.36
     szóci
    0.35
    makeatletter
    0.35
    partic
    0.35
     here
    0.35
     الحره
    0.35
     for
    0.34
     other
    0.34
    Act Density 0.174%

    No Known Activations