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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating dependencies or conditional relationships among elements

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

    modern words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    üyor
    -0.50
    帖最后由
    -0.48
    zdro
    -0.44
    ſelves
    -0.44
    bahaya
    -0.44
    ercito
    -0.42
    ۜ
    -0.42
    ajari
    -0.42
     punggung
    -0.41
    åringen
    -0.41
    POSITIVE LOGITS
     modern
    0.83
    Modern
    0.63
     moderne
    0.62
     modernen
    0.61
     Modern
    0.60
    modern
    0.57
    现代
    0.56
    StoryboardSegue
    0.55
     GenerationType
    0.54
     современных
    0.54
    Act Density 0.453%

    No Known Activations