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

    Neuronpedia

    INDEX
    Explanations

    enc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rs
    -0.06
    ccione
    -0.06
    /sm
    -0.06
    why
    -0.06
    (',',
    -0.06
     correctly
    -0.06
     almost
    -0.06
    TRL
    -0.06
    034
    -0.06
     Conclusion
    -0.06
    POSITIVE LOGITS
        
↵
    0.07
     будущ
    0.07
     Milk
    0.06
     مقر
    0.06
     накоп
    0.06
     jar
    0.06
    .)↵↵↵↵
    0.06
    Mathf
    0.06
    ="./
    0.06
    _TAC
    0.06
    Act Density 0.000%

    No Known Activations