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

    Neuronpedia

    INDEX
    Explanations

    explaining how things work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.47
    IN
    0.47
    tiers
    0.45
    not
    0.43
     الاسم
    0.43
    त
    0.42
    एन
    0.42
    styles
    0.42
     préoccup
    0.42
    𝐍
    0.41
    POSITIVE LOGITS
     Hampton
    0.52
     banyak
    0.50
     menjel
    0.50
    ὐ
    0.48
     حاجه
    0.46
     θε
    0.46
     αντι
    0.46
    olak
    0.46
    ták
    0.45
    өрд
    0.45
    Act Density 0.001%

    No Known Activations