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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    asp
    -0.08
     Remote
    -0.07
    可行性
    -0.07
    不起
    -0.07
    parable
    -0.06
     Feedback
    -0.06
    \xff
    -0.06
    ˹
    -0.06
     return
    -0.06
     spi
    -0.06
    POSITIVE LOGITS
     cheating
    0.07
    +i
    0.07
     Zeit
    0.07
    בחירות
    0.07
     litigation
    0.07
    팟
    0.07
     lawy
    0.07
    التزام
    0.07
    对他们
    0.06
     supremacy
    0.06
    Act Density 0.004%

    No Known Activations