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

    Neuronpedia

    INDEX
    Explanations

    instances of low-ranking attribute terms in research contexts

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

    non- phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    minecraftforge
    -0.43
     تضيفلها
    -0.38
     Macy
    -0.38
     geho
    -0.38
    BoxLayout
    -0.37
     دیکھیے
    -0.35
    likler
    -0.35
     Deposit
    -0.34
     you
    -0.33
     Bezir
    -0.33
    POSITIVE LOGITS
    ‐
    1.70
     ‐
    1.33
    ‑
    0.96
    ﴾
    0.96
    ־
    0.83
    ־ה
    0.71
    $--
    0.69
     [''
    0.68
    ﴿
    0.67
    ﹣
    0.65
    Act Density 0.026%

    No Known Activations