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

    Neuronpedia

    INDEX
    Explanations

    #define

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    倉
    -0.07
     parked
    -0.06
     соч
    -0.06
    _uart
    -0.06
     bật
    -0.06
    ках
    -0.06
     cộng
    -0.06
    ultz
    -0.06
     至
    -0.06
     quá
    -0.06
    POSITIVE LOGITS
    ?'
    0.07
    lasyon
    0.07
    0.07
    ga
    0.07
    .Sample
    0.07
    _SEC
    0.07
    rapped
    0.06
    ];
    0.06
     relação
    0.06
    _METADATA
    0.06
    Act Density 0.001%

    No Known Activations