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

    Neuronpedia

    INDEX
    Explanations

    justice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cał
    -0.07
    alaxy
    -0.07
     aproxim
    -0.07
     KAR
    -0.06
    _birth
    -0.06
     crib
    -0.06
     Hal
    -0.06
    /theme
    -0.06
    irá
    -0.06
     Cinema
    -0.06
    POSITIVE LOGITS
     justice
    0.07
     *&
    0.06
    (always
    0.06
     불
    0.06
    Ｅ
    0.06
    장을
    0.06
    sent
    0.06
     executed
    0.06
     dword
    0.06
     请求
    0.06
    Act Density 0.031%

    No Known Activations