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

    Neuronpedia

    INDEX
    Explanations

    pseudonymous addresses, often absent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tarjeta
    0.45
    MainWindow
    0.44
    Hearts
    0.43
    Leben
    0.42
    Capture
    0.40
    Yellow
    0.40
    individual
    0.40
    introduce
    0.40
    Card
    0.39
    RequestParam
    0.39
    POSITIVE LOGITS
     ansible
    0.46
     reglas
    0.42
     idioms
    0.41
     amid
    0.40
     ambiguities
    0.40
    崩溃
    0.39
     freezing
    0.39
     nouns
    0.39
     ambiguity
    0.39
     animals
    0.39
    Act Density 0.002%

    No Known Activations