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

    Neuronpedia

    INDEX
    Explanations

    affirmative replies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     борьбе
    0.72
    奖
    0.67
     ठो
    0.67
     ट्राई
    0.67
     कोरिया
    0.66
    错误的
    0.65
     prizes
    0.65
    డంలో
    0.65
    错误
    0.64
    తులను
    0.64
    POSITIVE LOGITS
     yes
    2.91
    Yes
    2.82
     Yes
    2.79
    yes
    2.52
     YES
    2.34
    YES
    2.12
     yeah
    1.98
     oui
    1.87
     Yeah
    1.87
    Oui
    1.85
    Act Density 0.364%

    No Known Activations