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
     assez
    -0.07
     söz
    -0.07
     suspects
    -0.06
     всегда
    -0.06
     TOO
    -0.06
    대표
    -0.06
    _create
    -0.06
    _normal
    -0.06
    氧
    -0.06
     toda
    -0.06
    POSITIVE LOGITS
     refin
    0.07
    aters
    0.07
    _completion
    0.07
     Ip
    0.06
     resale
    0.06
    ATOM
    0.06
     driveway
    0.06
     اخبار
    0.06
     decreased
    0.06
     Lomb
    0.06
    Act Density 0.001%

    No Known Activations