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

    Neuronpedia

    INDEX
    Explanations

    process and integrate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protectors
    0.44
    uz
    0.43
    aturally
    0.40
    like
    0.40
     as
    0.40
     높아
    0.40
     vysok
    0.39
     shelters
    0.38
    bathing
    0.38
     anxiety
    0.38
    POSITIVE LOGITS
    Travelling
    0.47
     Aufgrund
    0.46
     effectuées
    0.46
     aufgrund
    0.46
    ௭
    0.46
    ൭
    0.45
    Upon
    0.45
     réparation
    0.44
    ረሻ
    0.42
     devido
    0.42
    Act Density 0.001%

    No Known Activations