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

    Neuronpedia

    INDEX
    Explanations

    game score and tie-breaker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Net
    0.52
     net
    0.50
     Net
    0.50
     neto
    0.48
    net
    0.46
     nets
    0.46
    NET
    0.45
    ▣
    0.45
     Нет
    0.44
     نت
    0.44
    POSITIVE LOGITS
     sets
    0.80
     Sets
    0.77
     set
    0.74
     Set
    0.73
    Sets
    0.69
    sets
    0.67
    Set
    0.66
    セット
    0.64
    set
    0.63
     সেট
    0.54
    Act Density 0.013%

    No Known Activations