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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to secrecy and hidden information

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

    secret, secrets, secrecy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Demografia
    -0.68
     AspNetCore
    -0.66
    ########.
    -0.65
     ddelwed
    -0.64
    harusnya
    -0.60
     BorderSide
    -0.60
     GenerationType
    -0.59
    UrlResolution
    -0.57
     Sandman
    -0.57
     ſehen
    -0.57
    POSITIVE LOGITS
     secret
    1.50
    Secret
    1.34
     Secret
    1.32
    secret
    1.31
     SECRET
    1.28
     secrets
    1.15
     secreto
    1.13
    SECRET
    1.12
     secrecy
    1.05
     Geheim
    1.05
    Act Density 0.018%

    No Known Activations