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

    Neuronpedia

    INDEX
    Explanations

    resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    çĸij
    -0.27
    ério
    -0.27
    Mods
    -0.26
    -mounted
    -0.26
    licative
    -0.26
    åħ¶ä¸Ńæľī
    -0.26
    åĮ»éĻ¢
    -0.26
    ekte
    -0.25
    åŃIJ
    -0.25
    жен
    -0.25
    POSITIVE LOGITS
    å±ģèĤ¡
    0.27
    eries
    0.25
     annotation
    0.24
    åĭ¤åĬ³
    0.24
    (links
    0.23
     advertisement
    0.23
    å°¸ä½ĵ
    0.23
    steps
    0.23
     ashes
    0.23
    ADVERTISEMENT
    0.23
    Act Density 0.075%

    No Known Activations