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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical spaces or structures

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

    floors and spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.46
    -0.43
    AnchorTagHelper
    -0.41
     Preferencias
    -0.40
     <=",
    -0.40
     simplifié
    -0.38
    DispatchToProps
    -0.37
     sonriendo
    -0.37
    ungkin
    -0.36
    Notae
    -0.36
    POSITIVE LOGITS
     floors
    0.65
     upstairs
    0.57
     floor
    0.56
     downstairs
    0.53
    Floor
    0.53
     loft
    0.53
     Floors
    0.52
    awtextra
    0.51
    floor
    0.50
    UnusedPrivate
    0.50
    Act Density 0.005%

    No Known Activations