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

    Neuronpedia

    INDEX
    Explanations

    measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    隧
    -0.08
     air
    -0.08
    幡
    -0.07
     המע
    -0.07
    袒
    -0.07
    뮬
    -0.07
    侦察
    -0.07
    嗵
    -0.07
     gri
    -0.07
    挈
    -0.07
    POSITIVE LOGITS
    _INDEX
    0.08
    _ESCAPE
    0.08
     forma
    0.07
    哈
    0.07
    值得注意
    0.07
    しています
    0.07
     checker
    0.07
     imposes
    0.07
    cite
    0.07
     familiar
    0.07
    Act Density 0.005%

    No Known Activations