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

    Neuronpedia

    INDEX
    Explanations

    energy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ampionship
    -0.07
    Search
    -0.07
     Guidance
    -0.07
    _IND
    -0.07
    резидент
    -0.07
    _arch
    -0.06
    (CONFIG
    -0.06
    However
    -0.06
    쑤
    -0.06
     VMware
    -0.06
    POSITIVE LOGITS
     prêt
    0.07
    "is
    0.07
    裁定
    0.07
    ollar
    0.07
    ];
↵
↵
    0.07
    牙
    0.07
    /z
    0.07
    礼物
    0.06
    iddle
    0.06
     facts
    0.06
    Act Density 0.041%

    No Known Activations