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

    Neuronpedia

    INDEX
    Explanations

    LaTeX math symbols

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     di
    -0.64
     r
    -0.60
     '
    -0.59
     #
    -0.59
     p
    -0.57
     k
    -0.57
    nic
    -0.56
     n
    -0.56
     all
    -0.56
     da
    -0.55
    POSITIVE LOGITS
     }}$}
    1.24
    )");
    1.23
    }{*}{}
    1.18
     itſelf
    1.16
    )}</
    1.13
    "]));
    1.10
     myſelf
    1.10
    =$?
    1.07
     }</
    1.07
     kasarigan
    1.06
    Act Density 0.068%

    No Known Activations