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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     |
    0.50
     When
    0.47
      
    0.45
    When
    0.42
     So
    0.41
    Ĭ
    0.40
    Ī
    0.39
       
    0.39
    6
    0.39
    4
    0.39
    POSITIVE LOGITS
     интернете
    0.41
     fellow
    0.38
     ಕಬ್ಬಿಣ
    0.38
    മിഷ
    0.38
     মানুষের
    0.38
     manipulations
    0.37
     fiance
    0.36
     ಮಾಹಿತಿ
    0.36
     OPERATIONS
    0.35
    𝚎
    0.35
    Act Density 0.012%

    No Known Activations