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

    Neuronpedia

    INDEX
    Explanations

    language and text processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oxid
    -0.08
    ั้
    -0.07
     etter
    -0.07
     Filipino
    -0.06
    bagai
    -0.06
     hvor
    -0.06
     lowers
    -0.06
     Chile
    -0.06
    "]).
    -0.06
    etas
    -0.06
    POSITIVE LOGITS
     Apartment
    0.07
    club
    0.07
    oenix
    0.07
     ​
    0.07
    -archive
    0.07
    country
    0.07
    _SHOW
    0.06
     JNICALL
    0.06
     Mutation
    0.06
    TU
    0.06
    Act Density 0.000%

    No Known Activations