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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allowance
    -0.07
     Man
    -0.07
     Lady
    -0.06
    _ls
    -0.06
    OG
    -0.06
    -driving
    -0.06
     Das
    -0.06
     prices
    -0.06
     Human
    -0.06
     detectors
    -0.06
    POSITIVE LOGITS
    шается
    0.08
    ──
    0.07
    ा।↵↵
    0.06
    @Controller
    0.06
    multipart
    0.06
     아버지
    0.06
    perform
    0.06
    ี↵
    0.06
    –↵↵
    0.06
    .currentTime
    0.06
    Act Density 0.048%

    No Known Activations