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

    Neuronpedia

    INDEX
    Explanations

    even framing or depicting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     некоторые
    0.22
    ویی
    0.21
     حتی
    0.20
     zelfs
    0.20
     todavía
    0.20
     semblent
    0.20
     parecen
    0.19
     některé
    0.19
     siquiera
    0.19
     nadal
    0.19
    POSITIVE LOGITS
    Context
    0.23
     Context
    0.23
    swering
    0.22
    context
    0.22
    ize
    0.22
    setHeader
    0.22
     framed
    0.21
    stated
    0.20
     disclaimer
    0.20
     և
    0.20
    Act Density 0.049%

    No Known Activations