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

    Neuronpedia

    INDEX
    Explanations

    **code comments and delimiters**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ový
    0.70
     pulver
    0.67
    antera
    0.64
     propel
    0.62
    зне
    0.62
    ქმედ
    0.62
     рабочий
    0.61
     divulge
    0.60
    shire
    0.58
     cogn
    0.58
    POSITIVE LOGITS
     Tattha
    0.74
     TEMP
    0.70
     Pineapple
    0.70
     JTextField
    0.70
     FirebaseAuth
    0.67
    按摩
    0.67
    TEMP
    0.66
    【
    0.65
    Massage
    0.65
    「
    0.65
    Act Density 0.068%

    No Known Activations