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

    Neuronpedia

    INDEX
    Explanations

    University

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amento
    -0.07
     mint
    -0.07
     Shelby
    -0.06
    초등학교
    -0.06
    ô
    -0.06
     आई
    -0.06
     Apollo
    -0.06
     Fragen
    -0.06
     command
    -0.06
     Experiment
    -0.06
    POSITIVE LOGITS
    orgetown
    0.07
    BAT
    0.06
    .ec
    0.06
     skulls
    0.06
     Geography
    0.06
     cl
    0.06
    interopRequire
    0.06
    clazz
    0.06
    serde
    0.06
     Georgetown
    0.06
    Act Density 0.018%

    No Known Activations