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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    global
    -0.08
    race
    -0.07
    規模
    -0.07
    排序
    -0.07
    てくる
    -0.07
    small
    -0.07
    In
    -0.07
    鐘
    -0.07
     ya
    -0.07
    简
    -0.07
    POSITIVE LOGITS
    (video
    0.07
    䥽
    0.07
    (IT
    0.06
    élé
    0.06
    (SIG
    0.06
    pushViewController
    0.06
     openid
    0.06
    WSC
    0.06
    ހ
    0.06
    probe
    0.06
    Act Density 0.052%

    No Known Activations