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

    Neuronpedia

    INDEX
    Explanations

    references to a specific cave, particularly its name and related features

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

    cave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.67
     indis
    -0.57
    indis
    -0.47
     Drapeau
    -0.47
     Smiths
    -0.46
     London
    -0.46
    stylers
    -0.45
    relationship
    -0.44
    responsibility
    -0.43
     wheat
    -0.43
    POSITIVE LOGITS
     cave
    1.23
     Cave
    1.09
    Cave
    1.07
    cave
    1.07
     caves
    1.05
     cueva
    1.02
     Caves
    0.98
     Cuevas
    0.82
     grotte
    0.81
     caverns
    0.66
    Act Density 0.007%

    No Known Activations