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

    Neuronpedia

    INDEX
    Explanations

    even

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cocina
    -0.07
     رف
    -0.06
     Tf
    -0.06
     BoxDecoration
    -0.06
     sunk
    -0.06
     mül
    -0.06
    unable
    -0.06
    signin
    -0.06
    ทอง
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     gold
    0.07
     Petr
    0.06
     explaining
    0.06
     Maven
    0.06
     �
    0.06
    �
    0.06
    pton
    0.06
    Eat
    0.06
    하자
    0.06
     even
    0.06
    Act Density 0.001%

    No Known Activations