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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.58
    ↵
    0.48
     ~
    0.48
     User
    0.44
     :
    0.43
    0.43
     the
    0.42
     Page
    0.41
                 
    0.41
                     
    0.41
    POSITIVE LOGITS
     yatırım
    0.49
    𝓐
    0.49
    බන්ධ
    0.48
     मल्टीप्लाई
    0.47
    রত্ব
    0.46
     कोहली
    0.46
    securityMarks
    0.46
    କ୍
    0.46
     anarchy
    0.46
    ባት
    0.45
    Act Density 0.020%

    No Known Activations