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

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bee
    -0.08
    pho
    -0.08
    Phot
    -0.08
     PIT
    -0.08
    phot
    -0.08
     Bee
    -0.07
     phot
    -0.07
    итета
    -0.07
    ikt
    -0.07
     Literacy
    -0.07
    POSITIVE LOGITS
    igning
    0.08
    نك
    0.07
    ");
↵
↵
    0.07
    ");
↵
    0.07
    ماع
    0.07
     mnoho
    0.07
     sel
    0.07
     tentang
    0.07
    0.07
     distrib
    0.07
    Act Density 0.250%
    No Known Activations