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

    Neuronpedia

    INDEX
    Explanations

    the function or purpose behind actions or entities

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

    for / 为

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quidem
    -0.46
    VYMaps
    -0.43
    Surely
    -0.43
     RoutedEventArgs
    -0.42
    Mald
    -0.41
    Certainly
    -0.41
    WaitGroup
    -0.41
     doable
    -0.41
    RegressionTest
    -0.40
    umque
    -0.40
    POSITIVE LOGITS
    为
    0.81
     为
    0.79
    為
    0.76
     為
    0.76
    爲
    0.69
    给
    0.57
    providedIn
    0.55
    替
    0.54
    为你
    0.53
    为您
    0.51
    Act Density 0.003%

    No Known Activations