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

    Neuronpedia

    INDEX
    Explanations

    sections and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或许
    0.34
     ہوسکتا
    0.34
     _:
    0.32
    かもしれません
    0.32
    வோ
    0.32
     olabilir
    0.32
     parseFloat
    0.32
     año
    0.31
     asent
    0.31
    ப்பின
    0.31
    POSITIVE LOGITS
    chlor
    0.36
     lastly
    0.35
    Force
    0.34
     Tinggi
    0.33
     &
    0.32
    limit
    0.32
    Sweet
    0.31
    KEA
    0.31
    Chlor
    0.31
    𝗗
    0.31
    Act Density 0.482%

    No Known Activations