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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     souvis
    -0.07
    одейств
    -0.07
     Roy
    -0.07
     defe
    -0.07
    amaha
    -0.07
    identally
    -0.07
    markets
    -0.06
    marshaller
    -0.06
     tiger
    -0.06
    Jackson
    -0.06
    POSITIVE LOGITS
    _WEAPON
    0.07
    ่าก
    0.06
    925
    0.06
     والس
    0.06
     الل
    0.06
    *s
    0.06
    ouncement
    0.06
     Researchers
    0.06
    _PD
    0.06
     BPM
    0.06
    Act Density 0.001%

    No Known Activations