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

    Neuronpedia

    INDEX
    Explanations

    instances of code-related elements or functions

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

    output format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.76
    Personendaten
    -0.66
    AddTagHelper
    -0.63
     snippetHide
    -0.62
     resourceCulture
    -0.61
    Autoritní
    -0.61
     ſon
    -0.60
    StoryboardSegue
    -0.60
    httphttps
    -0.59
     noDo
    -0.58
    POSITIVE LOGITS
     etc
    0.55
     A
    0.44
     Using
    0.43
     Provinz
    0.42
     Diez
    0.42
     the
    0.41
    Và
    0.41
     S
    0.41
    סת
    0.41
    élément
    0.41
    Act Density 0.031%

    No Known Activations