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

    Neuronpedia

    INDEX
    Explanations

    Abstract concepts and beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Saudi
    0.44
    l
    0.44
     England
    0.44
     виру
    0.43
    strip
    0.42
    spark
    0.42
    <em>
    0.41
     Dubai
    0.40
    op
    0.39
    ino
    0.39
    POSITIVE LOGITS
     doctrines
    0.54
     condições
    0.48
     pertanto
    0.47
     neoplastic
    0.47
     beliefs
    0.47
     priors
    0.47
     periods
    0.46
     upgrades
    0.46
     akibat
    0.46
     entonces
    0.46
    Act Density 0.003%

    No Known Activations