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

    Neuronpedia

    INDEX
    Explanations

    destroyed, taken, vanished, murdered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     symptoms
    0.71
     enfermedades
    0.67
     заболевания
    0.64
     endangering
    0.63
     sintomi
    0.62
     illness
    0.61
     doenças
    0.61
     schlim
    0.61
    ymptoms
    0.59
     disorders
    0.59
    POSITIVE LOGITS
     Spark
    0.53
     Requirement
    0.52
     showcasing
    0.50
     Archive
    0.49
     Quantity
    0.49
     illustrating
    0.49
     uży
    0.48
     Preserve
    0.48
     TensorFlow
    0.48
     Enrich
    0.47
    Act Density 0.074%

    No Known Activations