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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical structures or boundaries

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

    fenced, walled, paved places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PropertyGroup
    -0.44
    വാ
    -0.42
    èdia
    -0.41
    Etimología
    -0.41
    NSObject
    -0.41
    currentThread
    -0.40
    etro
    -0.40
    ckså
    -0.39
     utafitiHapana
    -0.39
     Berto
    -0.39
    POSITIVE LOGITS
     fenced
    1.59
    fenced
    1.24
     Enclosed
    0.65
     enclosed
    0.64
    aarrggbb
    0.61
     walled
    0.59
     Fencing
    0.57
     fencing
    0.56
    walled
    0.56
     clô
    0.54
    Act Density 0.002%

    No Known Activations