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

    Neuronpedia

    INDEX
    Explanations

    measurements and rates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ink
    -0.07
    阻止
    -0.07
    带走
    -0.07
     StringTokenizer
    -0.07
    ออกแบบ
    -0.07
    UPS
    -0.07
     descri
    -0.07
     lastName
    -0.07
    .Look
    -0.06
     DPI
    -0.06
    POSITIVE LOGITS
    fld
    0.07
    ssue
    0.07
    愈加
    0.07
     Blonde
    0.07
    elta
    0.07
    ificantly
    0.07
    kad
    0.07
    兰州
    0.07
    ASHBOARD
    0.07
    -ajax
    0.07
    Act Density 0.019%

    No Known Activations