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

    Neuronpedia

    INDEX
    Explanations

    substantive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deterior
    -0.07
     LS
    -0.07
    érieur
    -0.06
     कल
    -0.06
     shortened
    -0.06
     pets
    -0.06
    できます
    -0.06
    \Image
    -0.06
    arus
    -0.06
     Tour
    -0.06
    POSITIVE LOGITS
     substantive
    0.11
    ани
    0.07
    ScreenState
    0.07
    Goods
    0.07
     knowing
    0.06
    .send
    0.06
    Gratis
    0.06
    unprocessable
    0.06
    Sugar
    0.06
     weave
    0.06
    Act Density 0.002%

    No Known Activations