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

    Neuronpedia

    INDEX
    Explanations

    sets and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fif
    0.48
     fold
    0.46
     hold
    0.46
     filtre
    0.45
     с
    0.44
     chart
    0.44
     проце
    0.44
    рур
    0.44
     cutoff
    0.43
     guerra
    0.43
    POSITIVE LOGITS
    \}
    0.45
    Counc
    0.41
    ${
    0.39
     বিদেশী
    0.38
    \}-
    0.38
    -\\
    0.38
    Sincerely
    0.38
    ürgen
    0.38
    (\{
    0.36
    =""/>
    0.36
    Act Density 0.014%

    No Known Activations