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

    Neuronpedia

    INDEX
    Explanations

    phrases related to competition and comparison

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

    rivals and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    simp
    -0.38
    itinéraire
    -0.37
     simp
    -0.36
     gern
    -0.35
     prés
    -0.34
    innig
    -0.34
    tage
    -0.34
    EXIT
    -0.33
     gerne
    -0.33
    cillas
    -0.32
    POSITIVE LOGITS
    comparable
    0.62
     comparable
    0.60
     rival
    0.59
     Comparable
    0.57
    IntoConstraints
    0.56
     rivals
    0.56
    媲
    0.56
    Comparable
    0.55
     competitor
    0.54
     Rival
    0.54
    Act Density 0.030%

    No Known Activations