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

    Neuronpedia

    INDEX
    Explanations

    future time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unacceptable
    -0.07
     Kl
    -0.06
     Antar
    -0.06
    .biz
    -0.06
     condemnation
    -0.06
     reservations
    -0.06
     beating
    -0.06
     weekend
    -0.06
     قم
    -0.06
     initiated
    -0.06
    POSITIVE LOGITS
     결정
    0.06
    '´
    0.06
    ُون
    0.06
     ~/.
    0.06
    なた
    0.06
    STALL
    0.06
    ัฒ
    0.06
     ativ
    0.06
    ContainerGap
    0.06
    　　　　 　
    0.06
    Act Density 0.038%

    No Known Activations