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

    Neuronpedia

    INDEX
    Explanations

    based on

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

    word-final morphemes such as common suffixes and contractions (clitics).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    Canon
    0.40
     verfügt
    0.38
    zetac
    0.36
    знав
    0.35
    截止
    0.35
    擅
    0.35
     Locator
    0.35
     μον
    0.34
    ୟ
    0.34
    安装
    0.34
    POSITIVE LOGITS
     השי
    0.43
     comparisons
    0.42
    ِينَ
    0.40
     kw
    0.40
    ફો
    0.39
    ዝና
    0.39
     yearly
    0.39
     समुच्चय
    0.39
     التربيع
    0.39
    )=(-
    0.38
    Act Density 0.000%

    No Known Activations