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

    Neuronpedia

    INDEX
    Explanations

    code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     survived
    -0.07
     rdr
    -0.06
     bq
    -0.06
    autoload
    -0.06
     연락
    -0.06
     enclosing
    -0.06
     ^.
    -0.06
     精
    -0.06
     EVE
    -0.06
     vuông
    -0.06
    POSITIVE LOGITS
     MILF
    0.06
    Hospital
    0.06
    Suit
    0.06
    osi
    0.06
     chlorine
    0.06
     गलत
    0.06
    ok
    0.06
    .Hit
    0.06
    不要
    0.06
    íny
    0.06
    Act Density 0.000%

    No Known Activations