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

    Neuronpedia

    INDEX
    Explanations

    references to safes and security-related concepts

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

    secure storage spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.63
    ImageContext
    -0.62
    Espèce
    -0.62
    outSlope
    -0.61
     geſch
    -0.59
    middels
    -0.58
     AspNetCore
    -0.58
    findpost
    -0.57
     onCreateView
    -0.57
    Carriera
    -0.57
    POSITIVE LOGITS
     vault
    0.66
    vault
    0.57
     Vault
    0.56
    Vault
    0.53
    Storage
    0.52
     coffre
    0.51
     storage
    0.50
     secure
    0.48
     security
    0.46
     Storage
    0.45
    Act Density 0.006%

    No Known Activations