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

    Neuronpedia

    INDEX
    Explanations

    inter-related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     visualizar
    0.44
     May
    0.41
    Download
    0.41
     majest
    0.41
    دو
    0.41
    Installation
    0.41
    ị
    0.40
     plantings
    0.40
    idopsis
    0.39
    five
    0.39
    POSITIVE LOGITS
     도움
    0.45
    bidden
    0.43
    所有人
    0.43
    别人的
    0.42
    价比
    0.42
     refinance
    0.40
     வீடு
    0.40
    र्मेंद्र
    0.40
    社
    0.40
     disorderly
    0.39
    Act Density 0.009%

    No Known Activations