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

    Neuronpedia

    INDEX
    Explanations

    specific actions or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     потому
    0.49
    believe
    0.49
     believe
    0.46
     BECAUSE
    0.46
     because
    0.44
    because
    0.44
    かもしれません
    0.44
    porque
    0.43
    বিশ্বাস
    0.42
    LAMP
    0.42
    POSITIVE LOGITS
     bitOp
    0.53
     czynności
    0.53
     brochure
    0.48
     locomotion
    0.47
     grupy
    0.47
     stationery
    0.47
     regler
    0.46
     bookcase
    0.46
     규칙
    0.46
     rhythm
    0.45
    Act Density 0.002%

    No Known Activations