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

    Neuronpedia

    INDEX
    Explanations

    signal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <main
    -0.07
     các
    -0.07
    协商
    -0.07
    جيد
    -0.06
     nations
    -0.06
    Listing
    -0.06
    读懂
    -0.06
    .calculate
    -0.06
    小组
    -0.06
    ﱵ
    -0.06
    POSITIVE LOGITS
    pected
    0.08
    匿名
    0.08
    reak
    0.07
    werp
    0.07
    duit
    0.07
     saliva
    0.07
    pect
    0.07
    orque
    0.07
    Ḍ
    0.07
     Lives
    0.07
    Act Density 0.008%

    No Known Activations