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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     ней
    -0.07
     diabetic
    -0.07
     Lebanese
    -0.06
     zpráv
    -0.06
     fitte
    -0.06
    ");
↵
↵
    -0.06
     enorm
    -0.06
     blur
    -0.06
     thế
    -0.06
    POSITIVE LOGITS
    gravity
    0.07
    Works
    0.06
     Tele
    0.06
     tele
    0.06
    Env
    0.06
     Fully
    0.06
     tutti
    0.06
     Generates
    0.06
     मध
    0.06
     pwd
    0.06
    Act Density 0.036%

    No Known Activations