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

    Neuronpedia

    INDEX
    Explanations

    attendance, arrival

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Houſe
    -1.23
     Efq
    -1.22
     Reſ
    -1.21
     Monfieur
    -1.20
     Anſ
    -1.20
     photolibrary
    -1.16
     Majefty
    -1.16
    ſelves
    -1.13
     Theſe
    -1.13
     houſe
    -1.11
    POSITIVE LOGITS
     of
    1.21
     in
    0.66
     to
    0.59
    ,
    0.58
     at
    0.56
     come
    0.55
     with
    0.55
     so
    0.53
     rate
    0.53
    .
    0.53
    Act Density 0.075%

    No Known Activations