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

    Neuronpedia

    INDEX
    Explanations

    don't retaliate, confront, engage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    วรร
    0.48
     Bạn
    0.46
     Gia
    0.45
     Leukemia
    0.45
     Δη
    0.44
     Oxid
    0.44
     Convers
    0.44
     انتق
    0.44
     स्वर्
    0.44
     Eater
    0.44
    POSITIVE LOGITS
     இல
    0.44
    etermined
    0.39
    "--
    0.38
     endeavor
    0.38
    裁
    0.37
     calcul
    0.37
    ளை
    0.37
    の結果
    0.37
     rates
    0.37
     agree
    0.37
    Act Density 0.012%

    No Known Activations