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

    Neuronpedia

    INDEX
    Explanations

    text structure elements

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ismillahirrah
    0.55
    Პ
    0.54
    ꔰ
    0.52
    <unused2087>
    0.51
    <unused2221>
    0.50
     উপজে
    0.50
    ുമുള്ള
    0.49
    さまざまな
    0.48
    দন্ত
    0.47
    <unused2101>
    0.47
    POSITIVE LOGITS
      
    0.97
     -
    0.93
       
    0.82
     --
    0.77
           
    0.76
     etc
    0.75
     +
    0.75
     -->
    0.73
     )
    0.72
    ....
    0.71
    Act Density 3.309%

    No Known Activations