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

    Neuronpedia

    INDEX
    Explanations

    end markers and breaks in text

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

    question response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    using
    -0.44
     using
    -0.44
    Spoljašnje
    -0.41
    hoeddwyd
    -0.40
     Decke
    -0.39
     Sélectionnez
    -0.39
    ClCompile
    -0.38
    jamientos
    -0.38
    ględ
    -0.38
     USING
    -0.36
    POSITIVE LOGITS
    0.69
    httphttps
    0.63
    MigrationBuilder
    0.54
     CURIAM
    0.54
    
    0.54
    征詢我
    0.53
    面目
    0.53
    存于互联网档案馆
    0.53
     NSFW
    0.52
    setVerticalGroup
    0.52
    Act Density 0.003%

    No Known Activations