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

    Neuronpedia

    INDEX
    Explanations

    not GPT or ChatGPT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     탐
    0.49
     ক্ষেত্র
    0.45
     additives
    0.44
     Bxh
    0.43
     selezione
    0.42
     راستہ
    0.42
     sightseeing
    0.41
    ସ
    0.41
     অতিরিক্ত
    0.40
    ওয়ার
    0.39
    POSITIVE LOGITS
     supremely
    0.53
    gera
    0.52
    ссов
    0.46
    vault
    0.45
    netlify
    0.45
    plus
    0.45
     самых
    0.44
     caught
    0.43
    卫生
    0.43
    حی
    0.43
    Act Density 0.000%

    No Known Activations