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

    Neuronpedia

    INDEX
    Explanations

    going

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -0.66
     سبورت
    -0.65
    Населення
    -0.60
     defaultstate
    -0.57
    oa̍t
    -0.57
    TagMode
    -0.57
    PRNewswire
    -0.56
     оригіналу
    -0.56
    ++
    -0.56
    SourceChecksum
    -0.56
    POSITIVE LOGITS
     to
    0.73
     on
    0.63
    to
    0.63
     are
    0.59
     To
    0.57
     were
    0.56
    .
    0.56
     TO
    0.54
    To
    0.54
    Rhestr
    0.48
    Act Density 0.025%

    No Known Activations