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

    Neuronpedia

    INDEX
    Explanations

    years and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਾਂ
    0.92
    ించ
    0.87
    står
    0.84
    忥
    0.84
    edere
    0.83
     நின்று
    0.83
    ৈতিক
    0.83
    xious
    0.83
    ప
    0.82
     odst
    0.82
    POSITIVE LOGITS
     effectively
    0.76
     trains
    0.74
     និង
    0.74
     debut
    0.73
     correspondent
    0.71
     sông
    0.69
     Conse
    0.69
    ProductName
    0.69
     Seda
    0.69
     origins
    0.69
    Act Density 0.212%

    No Known Activations