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

    Neuronpedia

    INDEX
    Explanations

    mathematical and random operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jih
    0.90
    क्य
    0.81
     |=
    0.78
    Cons
    0.78
    et
    0.75
    eties
    0.75
    珣
    0.74
    FH
    0.73
    薨
    0.73
     ={
    0.73
    POSITIVE LOGITS
     nero
    0.68
    ೊಳ
    0.68
     മാറ്റ
    0.66
    स्थिति
    0.63
     брен
    0.63
    random
    0.63
     podej
    0.62
     паў
    0.62
     abs
    0.62
     структур
    0.62
    Act Density 0.148%

    No Known Activations