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

    Neuronpedia

    INDEX
    Explanations

    data size units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     milliard
    0.66
     Millions
    0.66
    Millions
    0.64
     billions
    0.63
     millions
    0.62
     milhões
    0.61
     milioane
    0.61
     millioner
    0.57
     miliardi
    0.55
     مليون
    0.55
    POSITIVE LOGITS
     KB
    0.77
     kB
    0.72
     bytes
    0.69
    KB
    0.68
     Kb
    0.63
    Bytes
    0.63
     kb
    0.62
     kilobytes
    0.62
    kb
    0.61
    bytes
    0.60
    Act Density 0.009%

    No Known Activations