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

    Neuronpedia

    INDEX
    Explanations

    technical elaboration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mest
    0.44
    ເອ
    0.40
     động
    0.39
     Bây
    0.38
    िफिकेशन
    0.37
    भगवान
    0.37
     Tory
    0.37
     Duffy
    0.37
     ControllerBase
    0.36
     воспа
    0.35
    POSITIVE LOGITS
     microscope
    0.41
     졸
    0.41
    equiv
    0.39
    adillo
    0.38
    Sc
    0.37
    Focus
    0.37
     language
    0.37
    language
    0.36
    EOL
    0.36
     trick
    0.36
    Act Density 0.000%

    No Known Activations