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

    Neuronpedia

    INDEX
    Explanations

    take action, care, control, permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ईसाई
    0.40
     制
    0.40
    畫
    0.39
    画
    0.39
     subsidi
    0.38
     Toni
    0.38
     参数
    0.38
    伷
    0.38
    氚
    0.37
    isp
    0.36
    POSITIVE LOGITS
     assistance
    0.51
     help
    0.50
     lap
    0.45
    取る
    0.45
     permission
    0.45
    取り
    0.44
    resh
    0.44
     forward
    0.42
    Help
    0.42
    饒
    0.41
    Act Density 0.002%

    No Known Activations