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

    Neuronpedia

    INDEX
    Explanations

    specific entities and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     termasuk
    1.20
     jangan
    1.07
     fluctuate
    1.03
     goreng
    1.02
     sesuai
    0.97
     dapat
    0.96
     samano
    0.96
     lainnya
    0.95
     ditth
    0.94
     frown
    0.93
    POSITIVE LOGITS
     WWII
    1.05
    日本の
    1.03
    S
    0.96
    M
    0.92
    IUM
    0.89
     transplanted
    0.89
    美国
    0.89
     Kyoto
    0.88
    ся
    0.86
    Opera
    0.86
    Act Density 0.272%

    No Known Activations