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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �로
    -0.07
    orgot
    -0.07
    topic
    -0.06
    Magn
    -0.06
    URAL
    -0.06
     Matching
    -0.06
     supermarket
    -0.06
     Lunch
    -0.06
     Loren
    -0.06
    _Login
    -0.06
    POSITIVE LOGITS
     yöntem
    0.06
    .IsTrue
    0.06
     metals
    0.06
    _gc
    0.06
     Lace
    0.06
     qx
    0.06
     adversary
    0.06
     Appalach
    0.06
     vysoké
    0.06
    ¹
    0.06
    Act Density 0.001%

    No Known Activations