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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StringBuffer
    0.45
    Determine
    0.43
     इसलिए
    0.41
     undesirable
    0.40
    をご確認
    0.38
    このような
    0.38
    Unless
    0.38
    Prevent
    0.38
    したがって
    0.37
    Include
    0.37
    POSITIVE LOGITS
    简直
    0.80
     excellently
    0.69
     excellente
    0.68
     superb
    0.66
     wonderfully
    0.65
     excelente
    0.64
     terrific
    0.64
     magnifique
    0.64
     superbly
    0.64
     admirably
    0.61
    Act Density 0.003%

    No Known Activations