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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns, possessives, and words related to individuality

    oai_token-act-pair · gemini-2.0-flash

    own

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.66
     للمعارف
    -0.65
     externi
    -0.62
    InitVars
    -0.62
    ISupport
    -0.60
    ContentAsync
    -0.60
     سكانية
    -0.59
    @[+][
    -0.59
     ouverts
    -0.59
     Baillargeon
    -0.58
    POSITIVE LOGITS
     personal
    0.66
     EdgeInsets
    0.54
     myself
    0.54
     yourself
    0.54
    yourself
    0.53
     himself
    0.49
    TabIndex
    0.49
    selves
    0.48
     private
    0.48
     name
    0.47
    Act Density 3.607%

    No Known Activations