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

    Neuronpedia

    INDEX
    Explanations

    relationships and connections among entities or concepts

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

    knows / loves / believes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.46
    createCanvas
    -0.42
     dijeron
    -0.42
     have
    -0.40
     تضيفلها
    -0.40
     themselves
    -0.40
     nila
    -0.40
    ValueStyle
    -0.39
    ằ
    -0.39
    have
    -0.38
    POSITIVE LOGITS
     उसने
    0.77
     любит
    0.68
     knows
    0.66
     prefers
    0.63
     loves
    0.61
     thinks
    0.60
     знает
    0.60
    knows
    0.60
     believes
    0.60
     has
    0.60
    Act Density 0.067%

    No Known Activations