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

    Neuronpedia

    INDEX
    Explanations

    terms related to political systems and social structures

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

    Abstract nouns followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    human concepts and experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.55
     زیادی
    -0.52
    mockito
    -0.51
     additional
    -0.51
    tedly
    -0.51
     iniz
    -0.49
    *************/
    -0.49
     کمی
    -0.49
    IZE
    -0.48
    例文
    -0.47
    POSITIVE LOGITS
    ագրություններ
    0.91
     EconPapers
    0.83
    AutoScaleMode
    0.80
     елның
    0.76
     humaine
    0.72
     فريبيس
    0.71
    ValueStyle
    0.71
    writeFieldEnd
    0.70
     utafitiHapana
    0.69
     المعيارى
    0.68
    Act Density 0.761%

    No Known Activations