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

    Neuronpedia

    INDEX
    Explanations

    references to official statements and legal documents related to allegations or investigations

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

    According to [source] statements

    np_acts-logits-general · gemini-2.0-flash

    official statements and records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BorderRadius
    -0.62
    correre
    -0.61
     ویکی‌پدیا
    -0.61
    principalTable
    -0.56
     harapan
    -0.54
     ujednoznacz
    -0.54
    printLine
    -0.53
     sopp
    -0.51
    /-/
    -0.51
     linkovi
    -0.51
    POSITIVE LOGITS
     obtained
    0.87
     released
    0.82
     cited
    0.79
     quoted
    0.78
     accessed
    0.74
     leaked
    0.72
     seen
    0.71
     sighted
    0.70
     disclosed
    0.69
     uploaded
    0.69
    Act Density 0.202%

    No Known Activations