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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evolve
    -0.07
    EC
    -0.07
     speech
    -0.07
     obsessed
    -0.06
     morally
    -0.06
    parser
    -0.06
     Commission
    -0.06
     foc
    -0.06
     consultation
    -0.06
    nya
    -0.06
    POSITIVE LOGITS
     donating
    0.07
     probable
    0.06
     alum
    0.06
     kullanarak
    0.06
     Heater
    0.06
     servings
    0.06
     ем
    0.06
    nesota
    0.06
     Stellar
    0.06
    gan
    0.06
    Act Density 0.004%

    No Known Activations