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

    Neuronpedia

    INDEX
    Explanations

    efficiency and detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र्में
    0.49
     maîtrise
    0.49
    en
    0.48
    лі
    0.48
    ਵੀ
    0.47
    ishma
    0.47
    érant
    0.46
     zatim
    0.46
    áš
    0.46
     apparaît
    0.46
    POSITIVE LOGITS
     $
    0.59
    瓣
    0.48
     NIH
    0.45
     $\{
    0.44
      
    0.43
     urgent
    0.43
     چپ
    0.42
    <0x0D>
    0.42
     pea
    0.42
    0.41
    Act Density 0.002%

    No Known Activations