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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey a sense of connection or relationship between people

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

    difficult situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.35
     deportivos
    -0.35
     plegable
    -0.32
     deseas
    -0.32
     zapatos
    -0.31
     Benutzer
    -0.31
     eş
    -0.31
     voeren
    -0.30
     prohibido
    -0.30
     auswählen
    -0.30
    POSITIVE LOGITS
    :✨
    0.71
    ngdoc
    0.65
     OFDb
    0.62
    IntoConstraints
    0.62
    0.60
    SharedCtor
    0.60
     transférez
    0.60
    makeConstraints
    0.59
    hoeddwyd
    0.58
    IndentedString
    0.58
    Act Density 0.087%

    No Known Activations