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

    Neuronpedia

    INDEX
    Explanations

    questions seeking information or clarification

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

    Questions that start with question words

    np_acts-logits-general · gemini-2.0-flash

    asking for explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    URLException
    -0.57
     mogelijk
    -0.48
    Note
    -0.46
    rial
    -0.44
     Note
    -0.44
    query
    -0.42
     απε
    -0.42
     OkHttpClient
    -0.40
    ಿದೆ
    -0.40
    참고
    -0.40
    POSITIVE LOGITS
     tell
    1.21
     Tell
    1.14
    Tell
    1.12
     TELL
    1.00
     explain
    0.96
     Describe
    0.90
     describe
    0.89
    说说
    0.88
     расска
    0.88
    TELL
    0.87
    Act Density 0.080%

    No Known Activations