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

    Neuronpedia

    INDEX
    Explanations

    original

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    attacks
    -0.07
    weapon
    -0.07
    Pizza
    -0.07
     año
    -0.06
     matching
    -0.06
    (net
    -0.06
     turtles
    -0.06
     Meaning
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    तम
    0.07
    कन
    0.07
    .OrdinalIgnoreCase
    0.07
     술
    0.06
     بازیگر
    0.06
     kaliteli
    0.06
    Svc
    0.06
    階
    0.06
    اقل
    0.06
     피해
    0.06
    Act Density 0.009%

    No Known Activations