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

    Neuronpedia

    INDEX
    Explanations

    essential items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PROVIDED
    0.41
    ᄈ
    0.41
     popped
    0.40
     대상으로
    0.40
     pq
    0.40
    eville
    0.39
     WOULD
    0.39
    isz
    0.39
     Ö
    0.39
    birth
    0.39
    POSITIVE LOGITS
    Cet
    0.36
     Ree
    0.35
     coinvol
    0.35
    Realistic
    0.35
    жит
    0.34
    Treatment
    0.34
    رفة
    0.34
    Genuine
    0.34
     вступи
    0.33
    Confusion
    0.32
    Act Density 0.011%

    No Known Activations