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

    Neuronpedia

    INDEX
    Explanations

    guidelines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     benchmark
    -0.07
     EV
    -0.06
    justify
    -0.06
     critical
    -0.06
     folding
    -0.06
    named
    -0.06
     girls
    -0.06
     TEST
    -0.06
    рес
    -0.06
     rdr
    -0.06
    POSITIVE LOGITS
     abol
    0.07
     pocházet
    0.06
    ]:=
    0.06
    APPLE
    0.06
    』
    0.06
    asticsearch
    0.05
    อพ
    0.05
     Quando
    0.05
     �
    0.05
     위한
    0.05
    Act Density 0.002%

    No Known Activations