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

    Neuronpedia

    INDEX
    Explanations

    certain phrases and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اہمیت
    0.44
    的重要
    0.44
    ේෂ
    0.42
    的重要性
    0.42
     اهمیت
    0.41
     اہم
    0.40
     اهم
    0.38
     २
    0.38
    nej
    0.37
    浩
    0.37
    POSITIVE LOGITS
     وفق
    0.44
     bisogna
    0.43
    fashion
    0.42
     към
    0.41
     elevates
    0.41
    athletics
    0.41
    mechanism
    0.40
    according
    0.40
    BL
    0.40
     الناس
    0.40
    Act Density 0.004%

    No Known Activations