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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     picnic
    -0.07
    Ron
    -0.07
    tü
    -0.07
    场景
    -0.07
    鲀
    -0.07
    หว
    -0.07
     glean
    -0.07
     casc
    -0.07
    กระเป
    -0.07
     dapat
    -0.06
    POSITIVE LOGITS
     (“
    0.07
     começar
    0.07
     Elig
    0.07
     ('
    0.07
    uars
    0.07
    並將
    0.07
     ANC
    0.06
     partnering
    0.06
    裂缝
    0.06
    Υ
    0.06
    Act Density 0.093%

    No Known Activations