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

    Neuronpedia

    INDEX
    Explanations

    iconic and famous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ممكن
    0.40
     privés
    0.38
     weiteren
    0.37
     meerdere
    0.37
     rohkem
    0.36
     gewonnen
    0.35
     sparsim
    0.35
     pouvant
    0.35
     fudai
    0.34
     venant
    0.34
    POSITIVE LOGITS
     famously
    0.92
     infamous
    0.75
     iconic
    0.73
     знамени
    0.66
    有名な
    0.63
     famous
    0.61
     प्रसिद्ध
    0.59
    著名的
    0.59
    经典的
    0.58
     notorious
    0.58
    Act Density 0.806%

    No Known Activations