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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FREE
    -0.07
    GINE
    -0.07
    札
    -0.06
    運
    -0.06
     Ama
    -0.06
     Ratings
    -0.06
    Usuario
    -0.06
     теп
    -0.06
    确定
    -0.06
    ANG
    -0.06
    POSITIVE LOGITS
     rushes
    0.07
     Chí
    0.07
     Designed
    0.07
    щие
    0.06
    -б
    0.06
     however
    0.06
    .removeEventListener
    0.06
    .putInt
    0.06
     glGen
    0.06
     hashing
    0.06
    Act Density 0.247%

    No Known Activations