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

    Neuronpedia

    INDEX
    Explanations

    host

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rome
    -0.07
     Rubio
    -0.06
    .exchange
    -0.06
     adultery
    -0.06
    _vertical
    -0.06
    obic
    -0.06
     Greeks
    -0.06
     것입니다
    -0.06
    _gamma
    -0.06
     ppm
    -0.06
    POSITIVE LOGITS
    。↵↵
    0.08
    !")↵
    0.07
    ];
↵
↵
    0.07
    })↵↵↵
    0.07
    ».↵
    0.07
    );
↵
↵
    0.06
    _processes
    0.06
    	inter
    0.06
     indicative
    0.06
    *
↵
    0.06
    Act Density 0.018%

    No Known Activations