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

    Neuronpedia

    INDEX
    Explanations

    positive quality

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    有一定的
    0.45
    बड़े
    0.45
     ಪ್ರಮಾಣ
    0.44
     undertakings
    0.44
     최대한
    0.44
     Biggest
    0.44
     زیادہ
    0.43
     کافی
    0.43
     Largest
    0.42
     đủ
    0.42
    POSITIVE LOGITS
     excellent
    3.33
    excellent
    3.06
     excelente
    2.89
    Excellent
    2.89
     Excellent
    2.81
     fantastic
    2.75
     excelentes
    2.70
     excellente
    2.69
     superb
    2.47
     great
    2.44
    Act Density 1.189%

    No Known Activations