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

    Neuronpedia

    INDEX
    Explanations

    elements related to typography and character formatting

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

    Uppercase, lowercase, or general characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elemField
    -0.71
     transférez
    -0.63
    évaluateur
    -0.62
     transfieras
    -0.62
    нгред
    -0.62
     चीज़ों
    -0.60
    出版年
    -0.59
    DIPSETTING
    -0.59
    باردا
    -0.59
     utafitiHapana
    -0.59
    POSITIVE LOGITS
     letters
    0.39
     letter
    0.37
    letter
    0.37
    Letter
    0.35
     Tisch
    0.34
     character
    0.33
    LETTER
    0.33
     snippetHide
    0.32
     alphabet
    0.32
    Letters
    0.32
    Act Density 0.650%

    No Known Activations