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

    Neuronpedia

    INDEX
    Explanations

    Gemma team at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     podej
    0.64
     reach
    0.64
     finement
    0.62
    రుగులు
    0.61
     reaches
    0.60
    ृति
    0.59
     bergabung
    0.59
     soups
    0.58
    諗
    0.57
     cancellations
    0.57
    POSITIVE LOGITS
     podrían
    0.82
    Fer
    0.80
    PEC
    0.77
    Hlav
    0.77
    ﻗ
    0.77
    હાસ
    0.75
    कार्ट
    0.73
    ̿
    0.72
    कार्ड
    0.71
     과
    0.71
    Act Density 0.021%

    No Known Activations