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

    Neuronpedia

    INDEX
    Explanations

    cause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tượng
    -0.07
    持续
    -0.07
    了一系列
    -0.07
    input
    -0.07
    尝
    -0.07
    叹
    -0.07
    Analysis
    -0.07
    过了
    -0.07
    Visualization
    -0.06
    隙
    -0.06
    POSITIVE LOGITS
    𝚎
    0.08
     amps
    0.07
     أعلى
    0.07
    𝗖
    0.07
     funky
    0.07
    kończ
    0.07
    跑到
    0.07
    从来没
    0.07
     backyard
    0.07
    כלכלה
    0.07
    Act Density 0.005%

    No Known Activations