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

    Neuronpedia

    INDEX
    Explanations

    mathematical matrix or painting breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    牡
    0.40
    권
    0.40
    ᅩ
    0.39
     ELECTRON
    0.38
    클
    0.38
    зонта
    0.36
    एस्ट
    0.36
    꽝
    0.36
     listo
    0.36
     inscrito
    0.36
    POSITIVE LOGITS
     Including
    0.42
    一下
    0.41
     گلو
    0.38
     Incorpor
    0.38
    Eagle
    0.38
     Featuring
    0.37
    ಮಗೆ
    0.36
     تعالى
    0.36
    了一下
    0.35
     There
    0.35
    Act Density 0.000%

    No Known Activations