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

    Neuronpedia

    INDEX
    Explanations

    check and compare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    о
    0.46
    7
    0.46
    5
    0.43
    atonin
    0.43
    2
    0.42
    6
    0.42
    8
    0.41
    யோ
    0.40
     painfully
    0.39
     Rajas
    0.39
    POSITIVE LOGITS
     foodie
    0.50
    信息公示
    0.45
    িনবার্গ
    0.43
     sidebar
    0.41
     CheckKey
    0.41
     điểm
    0.41
     είναι
    0.40
    िवर्स
    0.39
     fluff
    0.39
     Brexit
    0.39
    Act Density 0.007%

    No Known Activations