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

    Neuronpedia

    INDEX
    Explanations

    references to various global issues and human behaviors

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

    inclusivity or totality

    np_acts-logits-general · gemini-2.0-flash

    everything, all, every

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.62
    󠁴
    -0.56
    ⤹
    -0.51
    orsese
    -0.50
    nesia
    -0.45
     createSprite
    -0.44
    Distribuzione
    -0.43
    UnusedPrivate
    -0.43
    Zacks
    -0.42
    Skor
    -0.42
    POSITIVE LOGITS
     Infórmanos
    0.60
     everything
    0.54
     every
    0.47
    everything
    0.46
     ویکی‌پدی
    0.44
     lahat
    0.44
     imaginable
    0.44
    every
    0.40
    ที่ยว
    0.40
    PDOException
    0.39
    Act Density 0.392%

    No Known Activations