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

    Neuronpedia

    INDEX
    Explanations

    settings and configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     set
    0.97
     সেট
    0.92
    セット
    0.82
     Set
    0.82
     sets
    0.75
     सेट
    0.75
     SET
    0.73
     seti
    0.72
     setzt
    0.71
     セット
    0.70
    POSITIVE LOGITS
    िंग्स
    0.54
    Sun
    0.53
    sun
    0.52
    ्ज
    0.46
    孙
    0.46
    sth
    0.45
    SUN
    0.44
    General
    0.44
    TINGS
    0.43
    Kong
    0.43
    Act Density 0.020%

    No Known Activations