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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iability
    -0.07
    .bin
    -0.07
    Tyler
    -0.07
     obraz
    -0.07
     bunny
    -0.07
    skills
    -0.06
    _detector
    -0.06
    acier
    -0.06
    _left
    -0.06
    Generating
    -0.06
    POSITIVE LOGITS
     Contributions
    0.07
     Apply
    0.06
    кового
    0.06
    /assert
    0.06
     Bravo
    0.06
    .Border
    0.06
     Uber
    0.06
    `),↵
    0.06
     Hydra
    0.06
    inspect
    0.06
    Act Density 0.079%

    No Known Activations