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

    Neuronpedia

    INDEX
    Explanations

    depends on scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lysis
    0.50
     optimise
    0.48
    优化
    0.47
    HS
    0.46
     ഉപ
    0.44
    ettu
    0.43
     বয়
    0.43
    DS
    0.42
    asse
    0.42
    र्न
    0.42
    POSITIVE LOGITS
     thrilled
    0.55
     awaited
    0.52
     forthwith
    0.52
     according
    0.49
     owed
    0.49
    に行く
    0.49
     Kreuz
    0.49
     uttered
    0.49
    ალაქ
    0.48
     tormented
    0.48
    Act Density 0.000%

    No Known Activations