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

    Neuronpedia

    INDEX
    Explanations

    summarize/review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ularity
    -0.07
     đoạn
    -0.07
    178
    -0.06
     ignorance
    -0.06
    ware
    -0.06
    胶
    -0.06
    ilde
    -0.06
    -power
    -0.06
    630
    -0.06
    彡
    -0.06
    POSITIVE LOGITS
     +%
    0.07
    _Camera
    0.07
    :"+
    0.07
     gì
    0.06
    玩
    0.06
    урн
    0.06
    ayız
    0.06
     внутріш
    0.06
     Persona
    0.06
    (sender
    0.06
    Act Density 0.032%

    No Known Activations