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

    Neuronpedia

    INDEX
    Explanations

    references to entry points or gateways in various contexts

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

    front door entrances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ModelAndView
    -0.46
    łoż
    -0.38
     mostaza
    -0.37
    ContentValues
    -0.35
     Egipto
    -0.35
    dataProvider
    -0.34
     missione
    -0.34
    Weights
    -0.34
     konserv
    -0.34
     mécan
    -0.33
    POSITIVE LOGITS
    door
    0.74
     doorstep
    0.74
     porch
    0.73
     doorbell
    0.72
     door
    0.68
     Door
    0.67
     doorways
    0.66
     DOOR
    0.65
     doorway
    0.63
     stoop
    0.62
    Act Density 0.007%

    No Known Activations