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

    Neuronpedia

    INDEX
    Explanations

    yes/no/true/false answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    他们
    0.43
    MODEL
    0.41
    guests
    0.40
    कोई
    0.39
    燼
    0.39
    DOMstrings
    0.39
    他們
    0.39
    effetto
    0.38
    ющий
    0.38
     MyApplication
    0.38
    POSITIVE LOGITS
    yes
    0.59
     Yes
    0.57
    Yes
    0.57
     yes
    0.55
     YES
    0.55
     boolean
    0.54
    YES
    0.54
    BooleanField
    0.52
    boolean
    0.50
     হ্যাঁ
    0.50
    Act Density 0.053%

    No Known Activations