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

    Neuronpedia

    INDEX
    Explanations

    verbal interactions and their clarity in communication

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

    string length and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.50
    ustand
    -0.38
    gaande
    -0.37
    новништво
    -0.33
    blusa
    -0.33
    estars
    -0.33
    Тарихы
    -0.32
     Travail
    -0.32
    rhosis
    -0.32
    èlement
    -0.32
    POSITIVE LOGITS
    AddTagHelper
    0.66
    BeginContext
    0.65
    舌
    0.56
    manteau
    0.55
    WithIOException
    0.54
     mouthful
    0.51
    IUrlHelper
    0.51
    DoubleQuotes
    0.50
     صوتيه
    0.50
    帖最后由
    0.50
    Act Density 0.294%

    No Known Activations