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

    Neuronpedia

    INDEX
    Explanations

    reversing text or sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    への
    0.94
    Featuring
    0.92
    Every
    0.91
    Measuring
    0.91
    Some
    0.90
    representing
    0.90
    Calculating
    0.89
     करणाऱ्या
    0.89
    The
    0.89
    Substituting
    0.88
    POSITIVE LOGITS
     diseases
    0.87
     disorder
    0.83
     disease
    0.82
     artifacts
    0.81
     organisms
    0.80
     appliances
    0.78
     ailments
    0.78
     reefs
    0.77
     disorders
    0.77
     successes
    0.77
    Act Density 0.001%

    No Known Activations