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

    Neuronpedia

    INDEX
    Explanations

    Quantum, Azure, IndexedDB, Code, CLI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    天堂
    0.40
     Etern
    0.39
    abhave
    0.39
     رای
    0.38
     제출
    0.37
     Career
    0.37
     उगा
    0.37
    なんで
    0.37
     ناقابل
    0.36
    HIGHLIGHT
    0.36
    POSITIVE LOGITS
     repeater
    0.47
     passengers
    0.46
     mechanisms
    0.45
     discontinuities
    0.44
     offspring
    0.44
     motorcycles
    0.44
     intercellular
    0.43
     slits
    0.42
     ชั้น
    0.41
     obnoxious
    0.41
    Act Density 0.001%

    No Known Activations