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

    Neuronpedia

    INDEX
    Explanations

    Physics equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agga
    -0.09
     southern
    -0.08
    sun
    -0.08
    群众
    -0.08
     Chennai
    -0.08
    .xpath
    -0.08
     Southern
    -0.08
     receptive
    -0.08
    ants
    -0.08
    Whitelist
    -0.07
    POSITIVE LOGITS
    (Constants
    0.07
     mise
    0.07
     Constants
    0.07
     potreb
    0.07
    سط
    0.07
     EDGE
    0.07
     technologies
    0.07
    LATEST
    0.07
     praktik
    0.07
    是多少
    0.07
    Act Density 0.005%

    No Known Activations