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

    Neuronpedia

    INDEX
    Explanations

    depending on a condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     either
    0.78
     ngược
    0.72
     கோட்ப
    0.72
     BasicDBObject
    0.71
    either
    0.71
     that
    0.68
     Wissen
    0.66
     neither
    0.64
    MONG
    0.63
    昭
    0.63
    POSITIVE LOGITS
    larda
    0.77
     lockout
    0.72
     rise
    0.71
    uldron
    0.71
     राह
    0.69
     liaison
    0.68
    ご
    0.68
    la
    0.67
     influx
    0.66
     인기
    0.66
    Act Density 0.056%

    No Known Activations