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

    Neuronpedia

    INDEX
    Explanations

    out of office emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     describ
    -0.09
     tensile
    -0.09
     antrop
    -0.09
     spatial
    -0.08
     tun
    -0.08
     Holocaust
    -0.08
     anne
    -0.08
     outright
    -0.08
     वर्ण
    -0.08
     Messiah
    -0.07
    POSITIVE LOGITS
    Notifications
    0.15
    .notifications
    0.14
     inbox
    0.13
    Inbox
    0.13
     notifications
    0.13
    _notifications
    0.13
    notifications
    0.13
     Inbox
    0.12
     Notifications
    0.12
    通知
    0.11
    Act Density 0.043%

    No Known Activations