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

    Neuronpedia

    INDEX
    Explanations

    semicolons and closing curly braces, indicating the end of code blocks or statements

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

    end of code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.79
     ujednoznacz
    -0.77
     invokingState
    -0.69
    rungsseite
    -0.66
     betweenstory
    -0.64
     يتيمه
    -0.63
    AddTagHelper
    -0.60
    IUrlHelper
    -0.60
    -0.58
    galus
    -0.58
    POSITIVE LOGITS
     précédents
    0.42
     secundario
    0.40
     navideño
    0.40
     venganza
    0.39
     romántica
    0.37
     cœurs
    0.36
     antemano
    0.36
     segunda
    0.34
     masculinos
    0.34
     inesperado
    0.33
    Act Density 0.007%

    No Known Activations