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

    Neuronpedia

    INDEX
    Explanations

    references to security or preventive actions

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

    preventive or protective actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kowalski
    -0.55
     Reif
    -0.52
     Schlafzimmer
    -0.47
    yor
    -0.45
     Palacios
    -0.45
     garagem
    -0.44
     coffees
    -0.43
     parkir
    -0.43
    copy
    -0.43
     Universitaria
    -0.43
    POSITIVE LOGITS
     measures
    1.55
    measures
    1.45
     Measures
    1.45
    Measures
    1.42
     MEASURES
    1.16
    措施
    1.13
     Maßnahmen
    1.10
     medidas
    1.09
     mesures
    1.05
     misure
    1.05
    Act Density 0.009%

    No Known Activations