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
    ORB
    -0.07
     warm
    -0.07
    mill
    -0.06
    orb
    -0.06
     anti
    -0.06
     우리는
    -0.06
    Baş
    -0.06
    yun
    -0.06
     DOMAIN
    -0.06
    _gift
    -0.06
    POSITIVE LOGITS
    鮮
    0.07
    ]‏
    0.07
    */↵↵↵
    0.07
     '''
↵
    0.07
    }

↵
    0.07
     Slovenia
    0.07
    ]]
↵
    0.07
    %).↵↵
    0.06
    _VAR
    0.06
    ermalink
    0.06
    Act Density 0.017%

    No Known Activations