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

    Neuronpedia

    INDEX
    Explanations

    code, ingredients, relaxation, technical steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кому
    0.52
     робити
    0.52
     якщо
    0.51
     价
    0.51
     שי
    0.50
    𝓐
    0.49
     ہونا
    0.49
     дуже
    0.49
     有限
    0.49
    紾
    0.49
    POSITIVE LOGITS
     plugins
    0.43
     controls
    0.42
     heterogeneous
    0.42
     meta
    0.42
    ངས་
    0.42
     androidx
    0.42
     metadata
    0.41
     Slack
    0.41
     metab
    0.41
     administra
    0.41
    Act Density 0.004%

    No Known Activations