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

    Neuronpedia

    INDEX
    Explanations

    study and information sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    第一題
    0.22
    缛
    0.22
    پیگنڈ
    0.21
     سینٹی
    0.21
    蠹
    0.21
    ﺓ
    0.20
    ល់
    0.20
    قية
    0.20
     अधि
    0.20
    ؍
    0.20
    POSITIVE LOGITS
     a
    0.26
     for
    0.25
     in
    0.24
    '
    0.24
     power
    0.23
    d
    0.23
     of
    0.23
     se
    0.22
     s
    0.22
     O
    0.22
    Act Density 0.006%

    No Known Activations