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
     Nacional
    -0.07
    ifié
    -0.06
     досвід
    -0.06
    แก
    -0.06
    eligible
    -0.06
    �
    -0.06
     центра
    -0.06
    œ
    -0.06
    .datab
    -0.06
    ę
    -0.06
    POSITIVE LOGITS
     khung
    0.07
     website
    0.07
     कप
    0.07
     Bü
    0.07
    (coeff
    0.06
     corporation
    0.06
    ैसल
    0.06
     picking
    0.06
    XL
    0.06
     stalking
    0.06
    Act Density 0.028%

    No Known Activations