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

    Neuronpedia

    INDEX
    Explanations

    /activity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᵗ
    -0.08
    航母
    -0.07
    菩
    -0.07
    wishlist
    -0.06
    读后
    -0.06
    时间和
    -0.06
    IOException
    -0.06
    مدن
    -0.06
    伤病
    -0.06
    跗
    -0.06
    POSITIVE LOGITS
     ----------------
    0.07
    “This
    0.07
     proxy
    0.07
     установ
    0.07
     DIS
    0.07
     preferred
    0.06
    (packet
    0.06
     Clarke
    0.06
    >ID
    0.06
    ドラ
    0.06
    Act Density 0.000%

    No Known Activations