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

    Neuronpedia

    INDEX
    Explanations

    identity or relationship

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \n
    -0.07
    ीब
    -0.07
    :])↵
    -0.07
    Ports
    -0.07
    })
↵
↵
    -0.06
    }`);↵
    -0.06
     At
    -0.06
    )}>↵
    -0.06
    특별시
    -0.06
     willingness
    -0.06
    POSITIVE LOGITS
     눈을
    0.07
    itably
    0.07
    _pause
    0.06
    ekten
    0.06
    hardt
    0.06
    .Magic
    0.06
    -addons
    0.06
    -К
    0.06
     endeavor
    0.06
    ischen
    0.06
    Act Density 0.166%

    No Known Activations