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

    Neuronpedia

    INDEX
    Explanations

    references to significant individuals and their contributions

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

    Follows personal pronouns or mentions of people

    np_acts-logits-general · gemini-2.0-flash

    stories told about loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.39
     kropp
    -0.39
     sitten
    -0.37
    NewUrlParser
    -0.37
    abol
    -0.37
    Enllaces
    -0.36
     kiệm
    -0.36
     PyTuple
    -0.36
    béco
    -0.36
     viewType
    -0.36
    POSITIVE LOGITS
     heartbroken
    0.47
    FXMLLoader
    0.46
     posthum
    0.45
     mourners
    0.44
     NgModule
    0.43
     mourned
    0.43
    OGND
    0.43
    Tributes
    0.43
     tears
    0.42
     كومونز
    0.42
    Act Density 0.073%

    No Known Activations