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

    Neuronpedia

    INDEX
    Explanations

    citation needed relevant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আহমে
    0.43
    面对
    0.42
    उँ
    0.39
     categorized
    0.39
     deems
    0.39
     honoured
    0.39
    த்துள்
    0.38
    传入
    0.38
    뛸
    0.38
     reimag
    0.38
    POSITIVE LOGITS
     expts
    0.55
     revistas
    0.55
     arxiv
    0.53
     JHEP
    0.49
     první
    0.48
     ApJ
    0.46
     اخیر
    0.46
     %``
    0.46
    Nature
    0.45
    obit
    0.44
    Act Density 0.000%

    No Known Activations