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

    Neuronpedia

    INDEX
    Explanations

    keywords followed by common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StarService
    0.51
     காவிரி
    0.50
     Defts
    0.47
     prosecution
    0.46
     putative
    0.45
    ;*/
    0.45
    Ꮀ
    0.45
     preventative
    0.44
    โร
    0.44
    ÇÕES
    0.44
    POSITIVE LOGITS
     to
    0.56
     அழகு
    0.52
    踽
    0.50
    imbing
    0.50
     собира
    0.49
     шабло
    0.49
     n
    0.49
    to
    0.49
     cách
    0.48
     বন্ধুরা
    0.48
    Act Density 0.000%

    No Known Activations