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

    Neuronpedia

    INDEX
    Explanations

    sports, festivals, and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    저
    0.52
     Low
    0.50
     저
    0.49
     LOW
    0.46
     rendah
    0.46
     low
    0.45
     subordination
    0.44
    Low
    0.44
    LOW
    0.42
    ብ
    0.41
    POSITIVE LOGITS
     promising
    0.49
    Festival
    0.41
     festivals
    0.40
     Located
    0.39
    atural
    0.38
     Paralympic
    0.37
     திறன்
    0.37
    Olympic
    0.37
     talented
    0.36
    Located
    0.36
    Act Density 0.001%

    No Known Activations