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

    Neuronpedia

    INDEX
    Explanations

    all the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ם
    0.64
    ように
    0.55
     only
    0.50
    ราะห์
    0.50
    ول
    0.50
    вання
    0.49
     numquam
    0.49
    कर
    0.49
    ка
    0.48
    り
    0.48
    POSITIVE LOGITS
    iteration
    0.70
    usions
    0.61
     demás
    0.55
    iterate
    0.52
    iterations
    0.52
    uding
    0.49
    ignment
    0.48
    usive
    0.47
    udes
    0.47
     takers
    0.46
    Act Density 0.081%

    No Known Activations