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

    Neuronpedia

    INDEX
    Explanations

    ==========

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     truck
    -0.08
     Brand
    -0.07
    кою
    -0.07
    rick
    -0.07
     municipal
    -0.07
    _RG
    -0.07
     subdiv
    -0.06
    ZN
    -0.06
     mamm
    -0.06
     trial
    -0.06
    POSITIVE LOGITS
    以为
    0.07
    /"+
    0.06
     jpeg
    0.06
     objc
    0.06
    (chat
    0.06
    /"
    0.06
     dolayı
    0.06
    ความร
    0.06
     ổ
    0.06
    oji
    0.06
    Act Density 0.001%

    No Known Activations