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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to global influence and power dynamics

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

    global world concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.53
    ⤒
    -0.50
     Rural
    -0.49
    WebElementEntity
    -0.49
     Италијани
    -0.48
    Referencie
    -0.48
     mecán
    -0.47
    irited
    -0.47
     traslado
    -0.47
     Locals
    -0.46
    POSITIVE LOGITS
    RegistryLite
    0.57
     صوتيه
    0.42
    StatusCodes
    0.41
     WORLD
    0.40
    BufferException
    0.39
     world
    0.38
     addObject
    0.37
    msgTypes
    0.37
     AppCompatTheme
    0.36
    world
    0.36
    Act Density 0.026%

    No Known Activations