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

    Neuronpedia

    INDEX
    Explanations

    text formats and generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ments
    0.86
     উচিত
    0.84
    urricular
    0.79
     صورت
    0.77
     bes
    0.77
    restassured
    0.73
     част
    0.73
     vena
    0.72
     konci
    0.72
     સામે
    0.71
    POSITIVE LOGITS
     paperback
    1.05
    <bos>
    1.01
    charAt
    0.96
    ี่ป
    0.91
     manuscript
    0.88
    ually
    0.87
    γι
    0.86
    fieldText
    0.86
    ător
    0.85
    णारा
    0.84
    Act Density 0.257%

    No Known Activations