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

    Neuronpedia

    INDEX
    Explanations

    skincare and acne

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    1.06
     as
    0.99
    1
    0.99
    ant
    0.93
    il
    0.89
    op
    0.88
     t
    0.87
    ther
    0.87
     for
    0.86
    iken
    0.85
    POSITIVE LOGITS
    М
    1.23
    ↵↵
    1.17
    お金
    1.16
    INSON
    1.10
     mastect
    1.09
     enfant
    1.08
    ２
    1.08
     arrêt
    1.06
    ༢
    1.05
     cardiaque
    1.03
    Act Density 0.007%

    No Known Activations