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

    Neuronpedia

    INDEX
    Explanations

    music playlists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     macro
    -0.07
     ramp
    -0.07
    orneys
    -0.07
    emporary
    -0.07
    vens
    -0.07
    olg
    -0.07
     portfolios
    -0.07
     scenario
    -0.07
    岳
    -0.07
    -conf
    -0.07
    POSITIVE LOGITS
     dancing
    0.07
     driving
    0.07
     ואז
    0.07
    combine
    0.07
     różnic
    0.06
     öldür
    0.06
     bitten
    0.06
    .bundle
    0.06
    rollable
    0.06
    퓰
    0.06
    Act Density 0.061%

    No Known Activations