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

    Neuronpedia

    INDEX
    Explanations

    lose motivation or interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Easing
    0.35
    Eigen
    0.35
    រួ
    0.35
     বৃদ্ধির
    0.34
     خواست
    0.34
     ክፍ
    0.33
    घा
    0.33
    fluss
    0.33
    стаў
    0.33
    Allows
    0.33
    POSITIVE LOGITS
     sight
    0.84
     track
    0.72
     touch
    0.68
    sight
    0.66
     momentum
    0.65
     faith
    0.64
     grip
    0.63
     sleep
    0.57
    grip
    0.57
     appetite
    0.57
    Act Density 0.037%

    No Known Activations