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

    Neuronpedia

    INDEX
    Explanations

    elements related to discussions, reports, and plans regarding regulatory or investigative actions

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

    reports or plans about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.90
    CloseOperation
    -0.84
    OGND
    -0.84
    yntaxException
    -0.82
    Portail
    -0.81
     kasarigan
    -0.79
    <unused51>
    -0.79
     مرئيه
    -0.79
    <unused47>
    -0.79
    <unused43>
    -0.79
    POSITIVE LOGITS
     ever
    0.29
    ev
    0.28
    ”
    0.28
    "
    0.28
    valueOf
    0.27
     recently
    0.27
     áll
    0.26
     te
    0.26
     not
    0.26
    ad
    0.25
    Act Density 0.113%

    No Known Activations