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

    Neuronpedia

    INDEX
    Explanations

    poetry and poetic writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bow
    1.15
    v
    0.98
     показателей
    0.96
     piecewise
    0.94
    d
    0.94
    ocia
    0.93
     Surround
    0.92
    burg
    0.90
    dul
    0.89
    vom
    0.89
    POSITIVE LOGITS
    erful
    1.22
    entially
    1.17
     laureate
    1.11
    луй
    1.04
     dobu
    1.04
     mortem
    1.03
    itical
    1.01
    츈
    1.00
    ্ড
    1.00
    ifical
    0.99
    Act Density 0.169%

    No Known Activations