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

    Neuronpedia

    INDEX
    Explanations

    languages and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     penduduk
    0.54
     terbaru
    0.51
     estadounidense
    0.51
     depois
    0.49
    것도
    0.49
     sebelah
    0.49
     empresas
    0.48
    많
    0.47
    cuador
    0.47
     integrantes
    0.47
    POSITIVE LOGITS
     разум
    0.50
     प्रूफ
    0.49
     pyridine
    0.45
    Syntax
    0.44
     soạn
    0.44
     cryptography
    0.44
     configura
    0.43
     malfunctions
    0.43
     chimiques
    0.42
     codons
    0.42
    Act Density 1.364%

    No Known Activations