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

    Neuronpedia

    INDEX
    Explanations

    programmer language types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ientos
    0.60
    ის
    0.59
    imo
    0.58
    itie
    0.58
    :
    0.57
    ames
    0.57
    ’
    0.56
     מר
    0.55
    pricht
    0.54
    보다는
    0.54
    POSITIVE LOGITS
     on
    0.71
    s
    0.68
     out
    0.66
     în
    0.66
     hanno
    0.66
     get
    0.65
     cellar
    0.65
     qRT
    0.65
     a
    0.63
     end
    0.63
    Act Density 0.075%

    No Known Activations