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

    Neuronpedia

    INDEX
    Explanations

    constructions related to installation processes and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Norwegian/Danish language fragments

    np_acts-logits-general · gemini-2.0-flash

    Norwegian language context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     varandra
    -1.39
     igång
    -1.24
     stället
    -1.19
    følgelig
    -1.19
     skolan
    -1.18
     barnen
    -1.13
     vägen
    -1.11
     berätt
    -1.11
     täv
    -1.06
     skolen
    -1.04
    POSITIVE LOGITS
     en
    0.80
     på
    0.70
     med
    0.67
     i
    0.60
     som
    0.60
     del
    0.60
     kan
    0.58
     den
    0.58
     sam
    0.57
     und
    0.55
    Act Density 0.067%

    No Known Activations