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

    Neuronpedia

    INDEX
    Explanations

    historically discussed technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myös
    0.52
    സ്തു
    0.51
     tiež
    0.49
     ebenfalls
    0.48
     גם
    0.46
     વિવિધ
    0.46
     également
    0.46
    También
    0.46
     atribut
    0.45
     ٹک
    0.45
    POSITIVE LOGITS
     historically
    0.66
     nowadays
    0.61
     Historically
    0.59
     Nowadays
    0.58
     damals
    0.56
     давно
    0.55
     сейчас
    0.54
    Historically
    0.54
     traditionally
    0.52
     दशकों
    0.52
    Act Density 0.092%

    No Known Activations