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

    Neuronpedia

    INDEX
    Explanations

    components and features related to gates and railings

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

    gates and fences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    艋
    -0.33
    taba
    -0.32
     heroes
    -0.32
     awaken
    -0.32
     theatre
    -0.31
     theater
    -0.30
     hero
    -0.30
     Kran
    -0.30
    cloudf
    -0.30
     chromos
    -0.30
    POSITIVE LOGITS
     fence
    0.93
     Fence
    0.88
    Fence
    0.83
     fencing
    0.80
    fence
    0.80
     fences
    0.78
     Fencing
    0.74
     gates
    0.71
     gate
    0.71
     Gate
    0.67
    Act Density 0.023%

    No Known Activations