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

    Neuronpedia

    INDEX
    Explanations

    global

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     damaging
    -0.08
    日产
    -0.07
    新生
    -0.07
     seeding
    -0.07
     существует
    -0.07
     Vietnam
    -0.07
    anonymous
    -0.07
     Knee
    -0.06
    放入
    -0.06
    _pid
    -0.06
    POSITIVE LOGITS
     циф
    0.09
    hyp
    0.07
     CORPOR
    0.07
     P
    0.07
     ];↵
    0.07
    visual
    0.07
    walk
    0.07
     Father
    0.07
    aub
    0.07
    江县
    0.07
    Act Density 0.002%

    No Known Activations