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

    Neuronpedia

    INDEX
    Explanations

    <|message|>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ాస్త
    -0.09
    ouse
    -0.09
     Lange
    -0.08
     somehow
    -0.08
    宅
    -0.08
    收费
    -0.08
    ાસ્ત
    -0.08
     laughing
    -0.08
    νομα
    -0.07
    竞争
    -0.07
    POSITIVE LOGITS
    <|message|>
    0.09
     প্রয়োজন
    0.08
     ngg
    0.08
    Consider
    0.07
    Recipient
    0.07
     हुन
    0.07
     ಗಣ
    0.07
      ↵
    0.07
    য়ের
    0.07
    まず
    0.07
    Act Density 0.217%

    No Known Activations