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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     debug
    -0.07
    debug
    -0.07
    moid
    -0.07
    ran
    -0.07
     terang
    -0.07
     correspondente
    -0.07
    Quit
    -0.07
    .color
    -0.07
     color
    -0.07
    POSITIVE LOGITS
     relying
    0.09
     நிலையில்
    0.08
     relied
    0.08
    只能
    0.08
     கே
    0.08
     relies
    0.08
    ので
    0.08
    是假
    0.08
     நிலைய
    0.08
     cams
    0.08
    Act Density 0.157%
    No Known Activations