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

    Neuronpedia

    INDEX
    Explanations

    loss of control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蒿
    0.47
     கிரக
    0.46
     पेनल
    0.45
    هلا
    0.43
    ष्कार
    0.43
     Forks
    0.43
     infrastrukt
    0.42
     tentunya
    0.41
     besta
    0.41
    ગાહી
    0.41
    POSITIVE LOGITS
     assay
    0.46
    ");
    0.43
    ovod
    0.43
     листопада
    0.42
     वे
    0.38
    ін
    0.38
    वे
    0.38
     |_{
    0.38
    模样
    0.37
     };
    0.37
    Act Density 0.001%

    No Known Activations