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

    Neuronpedia

    INDEX
    Explanations

    end of a sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.96
    ：
    0.93
    :',
    0.87
    :[
    0.85
     они
    0.83
    :**
    0.83
    :`
    0.82
    です
    0.77
    :*
    0.77
    They
    0.77
    POSITIVE LOGITS
    そこで
    1.01
     Consequently
    0.99
     Accordingly
    0.95
    Consequently
    0.95
    为此
    0.93
     accordingly
    0.91
     而
    0.90
    而
    0.89
     thereby
    0.88
    เพื่อให้
    0.87
    Act Density 0.246%

    No Known Activations