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
     spirits
    -0.07
     تی
    -0.06
    чаются
    -0.06
    /service
    -0.06
     самого
    -0.06
     treasurer
    -0.06
     racket
    -0.06
     efficiently
    -0.06
     Hos
    -0.06
    QRSTUVWXYZ
    -0.06
    POSITIVE LOGITS
     b
    0.07
    /d
    0.07
    .UserId
    0.06
     ide
    0.06
    830
    0.06
     damning
    0.06
     füh
    0.06
    quiring
    0.06
     천
    0.06
    ลำ
    0.06
    Act Density 0.098%

    No Known Activations