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

    Neuronpedia

    INDEX
    Explanations

    genus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ſeveral
    -1.32
     itſelf
    -1.32
     Jefus
    -1.30
     Efq
    -1.28
     myſelf
    -1.27
     Houſe
    -1.27
     ſever
    -1.25
     Monfieur
    -1.23
     houſe
    -1.22
     photolibrary
    -1.21
    POSITIVE LOGITS
     of
    0.83
     in
    0.68
     on
    0.68
     (
    0.67
     
    0.67
    .
    0.66
     is
    0.63
    ,
    0.61
     to
    0.60
     for
    0.60
    Act Density 0.047%

    No Known Activations