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

    Neuronpedia

    INDEX
    Explanations

    This is

    np_acts-logits-general · gemini-2.5-flash-lite

    finds tokens used for emphasis or section/heading formatting (markdown-style emphasis and similar formatting markers).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     altres
    0.26
     sommige
    0.22
     aşağıdaki
    0.21
     nedenle
    0.21
     سایر
    0.21
     dalších
    0.21
     whatnot
    0.21
     neler
    0.20
     bestimmte
    0.20
     etcétera
    0.20
    POSITIVE LOGITS
    これは
    0.43
     это
    0.40
     This
    0.39
    这是一个
    0.37
     これは
    0.37
    Это
    0.36
    This
    0.36
    这是
    0.36
     這個
    0.35
     Đây
    0.35
    Act Density 3.001%

    No Known Activations