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

    Neuronpedia

    INDEX
    Explanations

    BJ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mD
    -0.07
    ождение
    -0.06
     словами
    -0.06
     glGet
    -0.06
     Loki
    -0.06
     Ying
    -0.06
    emma
    -0.06
    data
    -0.06
     především
    -0.06
     principalmente
    -0.06
    POSITIVE LOGITS
     vegetarian
    0.07
    src
    0.07
    ,j
    0.06
    ад
    0.06
     }↵
    0.06
    332
    0.06
     Claim
    0.06
    知
    0.06
     abolish
    0.06
     labor
    0.06
    Act Density 0.004%

    No Known Activations