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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Con
    -0.07
     moed
    -0.07
    ernen
    -0.07
    reichen
    -0.07
    -case
    -0.07
    _case
    -0.07
    जी
    -0.07
     suf
    -0.07
     vat
    -0.07
     nat
    -0.07
    POSITIVE LOGITS
    0.09
     бары
    0.08
    ::~
    0.08
    荷
    0.07
    \Traits
    0.07
     万博
    0.07
    ыш
    0.07
     Simba
    0.07
     澳
    0.07
    cieš
    0.07
    Act Density 0.005%
    No Known Activations