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

    Neuronpedia

    INDEX
    Explanations

    knowledge across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Substances
    0.73
     Block
    0.68
     Met
    0.68
    colas
    0.68
     Signals
    0.66
     substances
    0.66
     Suppliers
    0.65
     block
    0.65
    ത്തേ
    0.65
     Chrom
    0.64
    POSITIVE LOGITS
     conoscenza
    0.97
     conhecimento
    0.96
     knowledge
    0.93
     conocimiento
    0.93
     знания
    0.90
    knowledge
    0.88
     conocimientos
    0.87
     conhecimentos
    0.87
    知识
    0.86
     знали
    0.82
    Act Density 0.000%

    No Known Activations