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

    Neuronpedia

    INDEX
    Explanations

    Space, time, tech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -1.16
     avoient
    -1.12
     varandra
    -1.12
    verwijspagina
    -1.11
     Diſ
    -1.11
     ujednoznacz
    -1.09
     Efq
    -1.09
     Monfieur
    -1.09
     étoient
    -1.09
     Reſ
    -1.08
    POSITIVE LOGITS
     and
    0.83
     of
    0.81
     in
    0.81
     for
    0.77
    .
    0.75
    ,
    0.66
     
    0.65
     (
    0.63
     on
    0.61
    ↵↵
    0.59
    Act Density 0.079%

    No Known Activations