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

    Neuronpedia

    INDEX
    Explanations

    terms related to identification and localization

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

    identify and locate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.42
    XmlAccessType
    -0.39
    انجليز
    -0.36
    WriteBarrier
    -0.34
    TestFixture
    -0.33
     referenties
    -0.31
    HasAnnotation
    -0.31
     ddelweddau
    -0.30
    abaikan
    -0.29
    ต่อ
    -0.28
    POSITIVE LOGITS
     identify
    0.95
     identifies
    0.92
    identify
    0.89
     Identify
    0.88
     identifying
    0.84
    Identifying
    0.81
     Identifying
    0.79
    Identify
    0.79
     identification
    0.77
     identificar
    0.74
    Act Density 0.106%

    No Known Activations