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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to progress, diversity, and personal impact

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

    diverse student backgrounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HandlerContext
    -0.55
    ActionCreators
    -0.52
     ContentValues
    -0.52
    BufferException
    -0.51
    MessageOf
    -0.47
    FunctionFlags
    -0.47
    Дерекк
    -0.47
    !*\
    -0.47
     Spal
    -0.46
    toThrow
    -0.46
    POSITIVE LOGITS
     kurie
    0.36
    maxcdn
    0.35
     mourut
    0.34
     insuffisamment
    0.32
     noDo
    0.32
    الإنجليزية
    0.31
    béco
    0.30
     która
    0.29
     biologie
    0.29
     ktorá
    0.29
    Act Density 0.040%

    No Known Activations