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

    Neuronpedia

    INDEX
    Explanations

    self-care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cared
    1.14
     caring
    1.07
     Caring
    1.01
     cares
    0.89
     caregiver
    0.84
     care
    0.81
    䂝
    0.80
     caretaker
    0.80
     catering
    0.79
     cuidar
    0.78
    POSITIVE LOGITS
     explode
    0.80
     গোলাপ
    0.72
     Explosion
    0.70
     flash
    0.69
    クトル
    0.68
     look
    0.67
     त्यौ
    0.65
    য়ো
    0.65
     publish
    0.65
     explodes
    0.65
    Act Density 0.001%

    No Known Activations