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

    Neuronpedia

    INDEX
    Explanations

    Expiration/Time-to-live

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worship
    -0.10
     Adm
    -0.09
     admired
    -0.08
     لفظ
    -0.08
    toupper
    -0.08
     Courage
    -0.08
     strcmp
    -0.08
     Bridge
    -0.08
     recognizable
    -0.08
     آب
    -0.07
    POSITIVE LOGITS
    期限
    0.13
     TTL
    0.13
     expiration
    0.13
    TTL
    0.13
     expiry
    0.12
     expires
    0.12
    Expiration
    0.12
     срока
    0.12
     ttl
    0.12
    expires
    0.11
    Act Density 0.008%

    No Known Activations