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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and auxiliary verbs frequently used in questions

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

    questions about time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    afficheront
    -0.59
    évaluateur
    -0.46
     mostrarán
    -0.46
    TypedDataSet
    -0.40
    Ef
    -0.40
     simplifié
    -0.39
    liceerd
    -0.38
    -0.37
    WaitGroup
    -0.37
     desplaz
    -0.36
    POSITIVE LOGITS
    Wann
    0.76
    Cuándo
    0.73
     kapan
    0.68
     wann
    0.68
    什么时候
    0.65
     cuándo
    0.63
     Wann
    0.62
    when
    0.60
    何时
    0.60
     Calendar
    0.59
    Act Density 0.010%

    No Known Activations