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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jefus
    -1.37
     Efq
    -1.22
     itſelf
    -1.19
     myſelf
    -1.19
     Majefty
    -1.17
     faſt
    -1.13
     photolibrary
    -1.10
     Monfieur
    -1.10
     purpoſe
    -1.09
     doubtnut
    -1.08
    POSITIVE LOGITS
    :
    0.82
     your
    0.69
     not
    0.62
     using
    0.58
     being
    0.57
     their
    0.56
    .
    0.56
     :
    0.55
     a
    0.55
     you
    0.54
    Act Density 0.052%

    No Known Activations