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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enan
    -0.07
    uggested
    -0.06
     присутств
    -0.06
    698
    -0.06
     Ep
    -0.06
     Schwe
    -0.06
     tokenize
    -0.06
    exact
    -0.06
    ennen
    -0.06
     Rh
    -0.06
    POSITIVE LOGITS
     unitOfWork
    0.07
    .BAD
    0.07
     Cabin
    0.07
     cabin
    0.07
    .IsTrue
    0.06
     fork
    0.06
    getPlayer
    0.06
     reson
    0.06
    .property
    0.06
    (frames
    0.06
    Act Density 0.169%

    No Known Activations