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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endcode
    -0.07
     contro
    -0.07
     Retrie
    -0.06
    (pattern
    -0.06
     gặp
    -0.06
     weekly
    -0.06
     مربع
    -0.06
     replied
    -0.06
     summer
    -0.06
    Sunday
    -0.06
    POSITIVE LOGITS
     kal
    0.07
    _bl
    0.07
     phận
    0.06
    μπ
    0.06
    �
    0.06
     स
    0.06
    بعد
    0.06
    �
    0.06
    -sm
    0.06
     colorWith
    0.06
    Act Density 0.003%

    No Known Activations