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

    Neuronpedia

    INDEX
    Explanations

    phase equilibrium, transition, formation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ward
    0.53
    o
    0.50
     ليب
    0.50
    ges
    0.49
     deplorable
    0.49
    student
    0.48
    collegiate
    0.48
    J
    0.47
    শতঃ
    0.47
    gency
    0.46
    POSITIVE LOGITS
     austen
    0.64
     Koval
    0.62
    '،
    0.62
     Guill
    0.61
     divul
    0.60
     Kuznet
    0.59
    ੰ
    0.57
     Baud
    0.56
     Ку
    0.56
     Rim
    0.55
    Act Density 0.005%

    No Known Activations