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

    Neuronpedia

    INDEX
    Explanations

    from/of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .week
    -0.08
     Increasing
    -0.07
    权限
    -0.07
    business
    -0.07
    .isPlaying
    -0.07
    ificação
    -0.07
    ACHE
    -0.06
    ره
    -0.06
    GameState
    -0.06
     hommes
    -0.06
    POSITIVE LOGITS
     Bran
    0.07
     outputPath
    0.07
     transmit
    0.06
     contain
    0.06
     referencing
    0.06
     Burl
    0.06
     Ana
    0.06
    /File
    0.06
     cutting
    0.06
     credible
    0.06
    Act Density 0.018%

    No Known Activations