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

    Neuronpedia

    INDEX
    Explanations

    feudal system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    1.59
    t
    1.58
    v
    1.58
    f
    1.51
    c
    1.50
    p
    1.45
    es
    1.44
    ش
    1.37
    y
    1.36
    s
    1.34
    POSITIVE LOGITS
     συνεχ
    0.89
     prosecutors
    0.79
    arence
    0.77
    ofan
    0.77
     commanders
    0.76
    selValue
    0.76
     περισσότε
    0.74
     μόνο
    0.74
     morceaux
    0.73
    ことなく
    0.73
    Act Density 0.001%

    No Known Activations