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

    Neuronpedia

    INDEX
    Explanations

    URL and web-related components

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

    user inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     philosophi
    -0.47
     viſ
    -0.46
     Inſ
    -0.43
     ſy
    -0.42
     ſur
    -0.42
     ſer
    -0.41
    ANDUM
    -0.41
     Conſ
    -0.40
     perſ
    -0.40
     ſch
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.83
    :✨
    0.69
    IUrlHelper
    0.54
    IndentedString
    0.49
    évaluateur
    0.48
    üyada
    0.48
    MessageOf
    0.47
    脚注の使い方
    0.44
     beginnetje
    0.43
    SharedCtor
    0.43
    Act Density 0.000%

    No Known Activations