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

    Neuronpedia

    INDEX
    Explanations

    most common

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这将
    0.45
     полного
    0.42
     остальные
    0.40
     смогут
    0.39
     خواهند
    0.38
     auraient
    0.38
     dovrà
    0.38
    可能会
    0.37
    renzia
    0.37
    szyst
    0.37
    POSITIVE LOGITS
     widely
    0.93
     popular
    0.84
     commonly
    0.82
     popularized
    0.81
     prevalent
    0.75
     often
    0.68
     często
    0.67
     பிரபலமான
    0.66
     famous
    0.66
     často
    0.66
    Act Density 0.623%

    No Known Activations