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
     prosecuting
    -0.07
     ERA
    -0.07
     scorer
    -0.07
    ere
    -0.06
     Shakespeare
    -0.06
    :P
    -0.06
     CSV
    -0.06
     DataType
    -0.06
     сосед
    -0.06
     shirt
    -0.06
    POSITIVE LOGITS
     INIT
    0.07
    .UserService
    0.07
    ."/
    0.06
     rall
    0.06
     پاسخ
    0.06
    swers
    0.06
     può
    0.06
    .StatusOK
    0.06
    ord
    0.06
     تل
    0.06
    Act Density 0.073%

    No Known Activations