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

    Neuronpedia

    INDEX
    Explanations

    non-negotiable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    মহ
    0.43
    Mar
    0.40
     ce
    0.39
     Mar
    0.38
    Ce
    0.38
    maras
    0.37
     মার
    0.36
     Yeon
    0.36
     मार
    0.36
     variance
    0.36
    POSITIVE LOGITS
    邝
    0.41
     Bur
    0.40
     Cus
    0.38
     Burke
    0.38
     dür
    0.38
     Burr
    0.38
    bur
    0.38
     Burk
    0.38
     Pennington
    0.37
     Kus
    0.37
    Act Density 0.007%

    No Known Activations