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

    Neuronpedia

    INDEX
    Explanations

    words related to government or the UK

    oai_token-act-pair · gemini-2.0-flash

    technical terminology in software development

    np_token-act-pair-logits · gpt-4o-mini

    Random excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ябре
    -0.59
    ➞
    -0.52
     kamar
    -0.49
     Fray
    -0.48
    سد
    -0.47
     sobr
    -0.47
    )|^{
    -0.47
    haku
    -0.47
    opardy
    -0.46
     évaluation
    -0.46
    POSITIVE LOGITS
    StructEnd
    0.63
     autorytatywna
    0.54
    ########.
    0.53
    SharedCtor
    0.51
    routeProvider
    0.50
    ēju
    0.50
    SharedDtor
    0.49
     дописавши
    0.49
    enskap
    0.49
    protoimpl
    0.48
    Act Density 2.072%

    No Known Activations