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

    Neuronpedia

    INDEX
    Explanations

    obtaining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fault
    -0.06
     Week
    -0.06
    avatar
    -0.06
     hover
    -0.06
     sty
    -0.06
    iyi
    -0.06
    Par
    -0.06
     gri
    -0.06
     흔
    -0.06
    ergency
    -0.06
    POSITIVE LOGITS
    .outer
    0.07
     ebenfalls
    0.07
     establish
    0.06
     matrimon
    0.06
    lookup
    0.06
     intervals
    0.06
    session
    0.06
    밍
    0.06
    taient
    0.06
     functor
    0.06
    Act Density 0.000%

    No Known Activations