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

    Neuronpedia

    INDEX
    Explanations

    -summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "The
    -0.07
     customs
    -0.07
     Sang
    -0.06
    �
    -0.06
    &utm
    -0.06
    ющее
    -0.06
    二二
    -0.06
     امن
    -0.06
     �
    -0.06
     zdravot
    -0.06
    POSITIVE LOGITS
    papers
    0.06
    oner
    0.06
    арамет
    0.06
     vain
    0.06
     wavelengths
    0.06
    (sel
    0.06
     recover
    0.06
    remium
    0.06
     هد
    0.06
    τή
    0.06
    Act Density 0.001%

    No Known Activations