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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     behavior
    -0.08
    ived
    -0.08
     minutes
    -0.07
    _login
    -0.07
    🧜
    -0.07
     adopted
    -0.07
     Created
    -0.07
     WS
    -0.07
    淘宝
    -0.07
    /sys
    -0.07
    POSITIVE LOGITS
    すると
    0.07
    かなり
    0.07
    狙击
    0.07
    ﻼ
    0.07
     Nik
    0.07
     שנית
    0.06
    ありが
    0.06
     Gundam
    0.06
    (up
    0.06
    穜
    0.06
    Act Density 0.005%

    No Known Activations