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

    Neuronpedia

    INDEX
    Explanations

    quantities and numerical descriptors

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

    number followed by items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.67
     مشين
    -0.63
     surla
    -0.57
    AnchorStyles
    -0.54
    StoryboardSegue
    -0.53
    ViewImports
    -0.52
    aarrggbb
    -0.52
    ✨:
    -0.52
    PostInfinity
    -0.52
    angering
    -0.51
    POSITIVE LOGITS
    appointment
    0.32
     spørgsmål
    0.32
    minyak
    0.31
     frem
    0.31
     deportivas
    0.31
    Enllaces
    0.31
     trous
    0.30
     températures
    0.30
     portefeuille
    0.30
     sanitarias
    0.29
    Act Density 0.015%

    No Known Activations