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

    Neuronpedia

    INDEX
    Explanations

    performance metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ne
    0.44
    ي
    0.43
    یم
    0.43
    Bea
    0.42
    िक
    0.42
    و
    0.42
    ام
    0.41
    मा
    0.41
    digits
    0.40
    دا
    0.40
    POSITIVE LOGITS
     двой
    0.56
     лига
    0.52
     cidad
    0.51
     synced
    0.50
    нан
    0.49
     игра
    0.49
     funda
    0.48
     felicit
    0.48
     prazo
    0.48
    ల్యే
    0.47
    Act Density 0.000%

    No Known Activations