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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unearth
    -0.07
    ैच
    -0.06
    ерим
    -0.06
    Uh
    -0.06
     Vegan
    -0.06
    еч
    -0.06
    993
    -0.06
     Maurice
    -0.06
     Treat
    -0.06
     MUT
    -0.06
    POSITIVE LOGITS
    .parentElement
    0.07
     collaborative
    0.07
    íž
    0.07
    encodeURIComponent
    0.07
     дити
    0.06
     ','.
    0.06
    (':')[
    0.06
    \",\"
    0.06
    /div
    0.06
    ([-
    0.06
    Act Density 0.001%

    No Known Activations