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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ränk
    -0.07
    PerPixel
    -0.07
    视线
    -0.07
     snap
    -0.07
     visitor
    -0.07
     cracking
    -0.07
     chromat
    -0.07
    (inertia
    -0.07
    .splice
    -0.07
    phrase
    -0.07
    POSITIVE LOGITS
    봇
    0.07
    房贷
    0.07
    嗳
    0.07
    体制机制
    0.06
    袄
    0.06
    洛
    0.06
    ᠲ
    0.06
     Avengers
    0.06
    �
    0.06
    泡沫
    0.06
    Act Density 0.018%

    No Known Activations