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
    331
    -0.06
    rhs
    -0.06
    点
    -0.06
     Certification
    -0.06
     psychologically
    -0.06
     skip
    -0.06
     superiority
    -0.06
     Id
    -0.06
     wrote
    -0.06
     slowdown
    -0.06
    POSITIVE LOGITS
     răng
    0.07
    まと
    0.06
     عرضه
    0.06
    (土
    0.06
     등을
    0.06
    `.`
    0.06
    @section
    0.06
    ("/:
    0.06
    (square
    0.06
     zoek
    0.06
    Act Density 0.014%

    No Known Activations