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

    Neuronpedia

    INDEX
    Explanations

    108

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Locations
    -0.07
    Remember
    -0.06
     Churches
    -0.06
    notice
    -0.06
     Remember
    -0.06
    Aceptar
    -0.06
    Yaw
    -0.06
    	where
    -0.06
    tags
    -0.06
    .observable
    -0.06
    POSITIVE LOGITS
     sells
    0.07
    arehouse
    0.07
     serum
    0.06
    ods
    0.06
    거
    0.06
     unicode
    0.06
    LI
    0.06
    ],[-
    0.06
    sampling
    0.06
     aug
    0.06
    Act Density 0.000%

    No Known Activations