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

    Neuronpedia

    INDEX
    Explanations

    links after website or here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    भाविक
    0.63
    ngthen
    0.63
    =?,
    0.61
    Suddenly
    0.59
    }+...
    0.57
    ènement
    0.57
    =?
    0.57
    షే
    0.56
    azole
    0.56
    ველი
    0.56
    POSITIVE LOGITS
     ([
    2.34
     https
    2.17
     [
    2.07
    :[
    2.01
    ([
    1.93
     [[
    1.84
    https
    1.83
     www
    1.77
     [<
    1.71
     (<
    1.70
    Act Density 0.293%

    No Known Activations