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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the sustainability and persistence of effects or benefits over time

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

    cause or effect phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.49
    harapkan
    -0.46
     marinho
    -0.44
     groet
    -0.44
     rêves
    -0.44
     huellas
    -0.43
    wakili
    -0.42
    Glej
    -0.42
    jalá
    -0.41
     Moscú
    -0.41
    POSITIVE LOGITS
    Personensuche
    0.63
    verwijspagina
    0.54
     autorytatywna
    0.52
    Diweddarwch
    0.47
     ویکی‌پدی
    0.46
    ItemBackground
    0.43
     rhestr
    0.43
    IntoConstraints
    0.41
     uska
    0.40
    ècie
    0.40
    Act Density 0.405%

    No Known Activations