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

    Neuronpedia

    INDEX
    Explanations

    asking a question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conferring
    0.48
     erlaubt
    0.45
    所示
    0.44
     bạn
    0.44
    نيا
    0.43
     REGULATIONS
    0.43
     confer
    0.43
     allow
    0.42
    Regulations
    0.42
    ⌓
    0.42
    POSITIVE LOGITS
     synchronously
    0.47
     quieter
    0.39
    nului
    0.38
     Expanded
    0.38
    ners
    0.37
     Poo
    0.37
    weets
    0.37
     subcluster
    0.37
     slower
    0.37
     ತಿಳ
    0.36
    Act Density 0.002%

    No Known Activations