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

    Neuronpedia

    INDEX
    Explanations

    institute names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chrono
    0.48
     sony
    0.45
    峹
    0.44
     Sx
    0.43
     QuantityOnHand
    0.43
     업체
    0.43
    𒋛
    0.42
     glandes
    0.42
     \|\
    0.42
     eux
    0.41
    POSITIVE LOGITS
    <0xE2>
    0.58
    ‑
    0.46
    We
    0.40
    Be
    0.40
    discipl
    0.40
    Celebrating
    0.39
    Branch
    0.39
    ​​​​
    0.39
    exerc
    0.39
    discipline
    0.39
    Act Density 0.009%

    No Known Activations