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

    Neuronpedia

    INDEX
    Explanations

    scoring or securing a win

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cittadini
    0.50
     viciss
    0.47
    ദ്ധതി
    0.46
     verursacht
    0.46
     waging
    0.46
    肪
    0.46
     verwenden
    0.46
     tentando
    0.45
     korišten
    0.45
    用於
    0.44
    POSITIVE LOGITS
    6
    0.76
    7
    0.76
    8
    0.75
    3
    0.72
    5
    0.72
    1
    0.71
    2
    0.71
    4
    0.65
     two
    0.57
     three
    0.57
    Act Density 0.002%

    No Known Activations