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

    Neuronpedia

    INDEX
    Explanations

    she

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sWith
    -0.07
    �
    -0.06
     丶
    -0.06
    dál
    -0.06
    іблі
    -0.06
    空
    -0.06
    었다
    -0.06
    ToList
    -0.06
     Popular
    -0.06
    ια
    -0.06
    POSITIVE LOGITS
     Vice
    0.08
    	Result
    0.07
    .method
    0.07
    Yeah
    0.07
     Pre
    0.06
     Perc
    0.06
     Stealth
    0.06
     RHS
    0.06
     Rogue
    0.06
     Owned
    0.06
    Act Density 0.000%

    No Known Activations