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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing possession or ownership

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

    Contractions ending in "ve"

    np_acts-logits-general · gemini-2.0-flash

    i've heard, i've told, i've never, you've really

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    -0.95
     the
    -0.88
     an
    -0.78
     our
    -0.68
     your
    -0.60
     another
    -0.59
     stato
    -0.54
     not
    -0.53
     this
    -0.53
    not
    -0.52
    POSITIVE LOGITS
    fjspx
    0.90
    TagMode
    0.83
    DockStyle
    0.83
    SceneManagement
    0.81
     ་་
    0.81
    AddTagHelper
    0.77
     оригіналу
    0.76
    rrggbb
    0.74
    EDEFAULT
    0.74
    IGraphics
    0.74
    Act Density 0.086%

    No Known Activations