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

    Neuronpedia

    INDEX
    Explanations

    post-apocalyptic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     用
    -0.07
    LEVEL
    -0.06
    ansion
    -0.06
     зависим
    -0.06
     Jenny
    -0.06
    Japan
    -0.06
    建
    -0.06
    хов
    -0.06
     goggles
    -0.06
     =================================================================================
    -0.06
    POSITIVE LOGITS
    _detail
    0.07
     tenure
    0.07
     Upgrade
    0.07
     texas
    0.06
    бол
    0.06
    thane
    0.06
     Dr
    0.06
     situaci
    0.06
    rade
    0.06
     Admir
    0.06
    Act Density 0.023%

    No Known Activations