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

    Neuronpedia

    INDEX
    Explanations

    people and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     its
    -2.08
    它
    -1.70
     Scritto
    -1.63
    它的
    -1.59
    ㎥
    -1.56
    Soorten
    -1.47
    initWithFrame
    -1.47
     qualcuno
    -1.45
     either
    -1.41
    或是
    -1.41
    POSITIVE LOGITS
     The
    1.75
     There
    1.69
     they
    1.69
     of
    1.62
     who
    1.58
     I
    1.55
     They
    1.54
     Their
    1.54
     From
    1.51
     for
    1.50
    Act Density 0.238%

    No Known Activations