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

    Neuronpedia

    INDEX
    Explanations

    references to ground or floor levels in various contexts

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

    ground level, stays, truth, plane

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.63
    AddTagHelper
    -0.58
    SharedCtor
    -0.57
     transfieras
    -0.57
     AssemblyTitle
    -0.55
    EndGlobalSection
    -0.52
    aarrggbb
    -0.52
     queſta
    -0.52
    $_['
    -0.51
    樣的
    -0.50
    POSITIVE LOGITS
     ground
    1.63
     Ground
    1.59
    Ground
    1.55
     GROUND
    1.51
    ground
    1.45
    GROUND
    1.26
     grond
    0.94
    地面
    0.91
     Grounds
    0.90
     grounds
    0.86
    Act Density 0.008%

    No Known Activations