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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating states or conditions in various tenses

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

    stating facts or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.80
     autorytatywna
    -0.80
     houſe
    -0.75
    parsedMessage
    -0.74
     Савезне
    -0.73
     initComponents
    -0.72
    évaluateur
    -0.71
     Italijanski
    -0.70
    ſelf
    -0.69
     ſche
    -0.68
    POSITIVE LOGITS
     beträgt
    0.44
     wynosi
    0.44
     Temperaturen
    0.42
     déterminé
    0.41
     sebesar
    0.40
     Verbrauch
    0.40
     mínimo
    0.39
     températures
    0.38
     rumahnya
    0.38
     inferiores
    0.37
    Act Density 0.118%

    No Known Activations