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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
    untary
    -0.06
    Border
    -0.06
     loro
    -0.06
     accusations
    -0.06
     Ont
    -0.06
    階
    -0.06
     Handlers
    -0.06
     або
    -0.06
    дут
    -0.06
    POSITIVE LOGITS
    长度
    0.07
    .copyOf
    0.06
     vùng
    0.06
     �
    0.06
    ].↵↵
    0.06
     embell
    0.06
    -space
    0.06
     tela
    0.06
    (test
    0.06
     학생
    0.06
    Act Density 0.000%

    No Known Activations