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

    Neuronpedia

    INDEX
    Explanations

    environmentalchangesunderstandfluctuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geben
    0.40
     célèbre
    0.40
     PHYSICS
    0.40
     hỏi
    0.40
     feita
    0.39
     customize
    0.39
     egypt
    0.39
     pregunt
    0.38
    ţiei
    0.38
     phylogeny
    0.38
    POSITIVE LOGITS
    ardon
    0.42
    ET
    0.41
    udsman
    0.40
    ፒ
    0.40
     ಹಾಗ
    0.39
    ಂಗ್
    0.39
     derog
    0.39
    LL
    0.38
    衮
    0.38
    <0xCF>
    0.38
    Act Density 0.000%

    No Known Activations