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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ppers
    -0.07
    peare
    -0.07
    放眼
    -0.07
     xmm
    -0.07
    _grupo
    -0.06
     haired
    -0.06
     bạc
    -0.06
    裡面
    -0.06
    𝆹
    -0.06
    ungs
    -0.06
    POSITIVE LOGITS
    qt
    0.08
     הש
    0.07
    records
    0.07
    庭审
    0.07
     authenticated
    0.07
    cta
    0.06
    穹
    0.06
    生产商
    0.06
    WithString
    0.06
    elocity
    0.06
    Act Density 0.155%

    No Known Activations