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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    分别
    -0.08
     trebalo
    -0.08
     मन्त्र
    -0.08
     little
    -0.08
     capital
    -0.07
     podéis
    -0.07
    Estos
    -0.07
    越来越
    -0.07
    莫
    -0.07
    edeut
    -0.07
    POSITIVE LOGITS
     Unlike
    0.15
     unlike
    0.14
     contrairement
    0.12
    Unlike
    0.12
     unusually
    0.11
     Compared
    0.10
     atyp
    0.10
     отличие
    0.10
     uniquely
    0.10
     unparalleled
    0.10
    Act Density 0.191%

    No Known Activations