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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to closure or shutting down

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

    Actions related to closing something

    np_acts-logits-general · gemini-2.0-flash

    closed doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]--;
    -0.66
     Brandt
    -0.60
    🏼
    -0.58
     FetchType
    -0.58
    PhysRev
    -0.57
     HasFactory
    -0.57
     CreateTagHelper
    -0.56
    velle
    -0.56
    ComponentScan
    -0.52
    +#+
    -0.52
    POSITIVE LOGITS
     doors
    0.99
    doors
    0.87
     hermé
    0.86
     shut
    0.82
    Shut
    0.79
     Shut
    0.79
     shuts
    0.78
    閉
    0.77
    MethodManager
    0.77
     shutters
    0.76
    Act Density 0.078%

    No Known Activations