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

    Neuronpedia

    INDEX
    Explanations

    bird in, if you, enough to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     relayed
    0.53
     treasury
    0.47
     Treas
    0.46
     Chipotle
    0.46
     Dry
    0.46
     into
    0.46
     Widodo
    0.45
     Mr
    0.45
     Arthur
    0.45
     Treasury
    0.45
    POSITIVE LOGITS
    9
    0.50
    ة
    0.49
    other
    0.47
    বাই
    0.46
    8
    0.45
    ක්
    0.44
    비
    0.43
    雨
    0.43
    マックス
    0.43
    5
    0.43
    Act Density 0.006%

    No Known Activations