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

    Neuronpedia

    INDEX
    Explanations

    Up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dk
    -0.07
    ("{}
    -0.06
    icopt
    -0.06
     north
    -0.06
     DXGI
    -0.06
    蓝
    -0.06
     tough
    -0.06
     bm
    -0.06
     cual
    -0.06
    ivatel
    -0.06
    POSITIVE LOGITS
    _semaphore
    0.09
    岁
    0.07
     woes
    0.07
    109
    0.07
    .abort
    0.07
     alınması
    0.07
     constitu
    0.07
    etically
    0.07
    _resolve
    0.07
    　ヽ
    0.06
    Act Density 0.001%

    No Known Activations