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

    Neuronpedia

    INDEX
    Explanations

    final answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ori
    0.44
     group
    0.41
    ates
    0.41
     tower
    0.39
    ust
    0.39
    tower
    0.38
     Tower
    0.38
     scores
    0.38
    ation
    0.37
     towering
    0.37
    POSITIVE LOGITS
    PYTHON
    0.54
     voluntarios
    0.52
     этим
    0.51
     Malgré
    0.51
     вас
    0.50
     Verarbeitung
    0.48
     Diseño
    0.48
     Guerre
    0.48
    减少
    0.47
     ваш
    0.46
    Act Density 0.001%

    No Known Activations