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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uir
    -0.07
    etchup
    -0.07
    ائه
    -0.07
    /><
    -0.07
    UNT
    -0.06
    062
    -0.06
    myp
    -0.06
    不安
    -0.06
    ته
    -0.06
    _checkbox
    -0.06
    POSITIVE LOGITS
     Cas
    0.07
     Got
    0.07
     Además
    0.06
    Conclusion
    0.06
     SOLUTION
    0.06
     Ideally
    0.06
    Images
    0.06
    є
    0.06
    -source
    0.06
    _h
    0.06
    Act Density 0.041%

    No Known Activations