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

    Neuronpedia

    INDEX
    Explanations

    references to software configuration and dependencies

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

    user turn start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.57
    BufferException
    -0.47
    oneofs
    -0.43
    蚪
    -0.41
    archiviato
    -0.40
    Litteratur
    -0.39
    CppMethod
    -0.39
    GEBURTSDATUM
    -0.38
    yntaxException
    -0.38
    CUSSION
    -0.37
    POSITIVE LOGITS
     springfox
    0.81
    Docket
    0.57
     Docket
    0.54
     kasarigan
    0.54
     pleaſure
    0.51
    ſchen
    0.48
    ſcher
    0.44
     dormitórios
    0.44
     Verſ
    0.42
    liceerd
    0.41
    Act Density 0.001%

    No Known Activations