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

    Neuronpedia

    INDEX
    Explanations

    states or defines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఉన్నాయి
    0.43
     einschließlich
    0.40
     چکے
    0.39
     위한
    0.39
    也都
    0.38
    也會
    0.38
     물론
    0.38
     خواهد
    0.37
    तरीय
    0.37
     ఉన్నారు
    0.37
    POSITIVE LOGITS
     whereby
    0.76
     waarbij
    0.69
    将
    0.55
     означает
    0.54
    让
    0.52
     позволяет
    0.51
     将
    0.50
     wherein
    0.50
     idea
    0.49
     заключается
    0.48
    Act Density 0.562%

    No Known Activations