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

    Neuronpedia

    INDEX
    Explanations

    phoenix references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.41
     Makita
    0.39
    ırma
    0.38
    ctime
    0.38
    Eating
    0.37
    ékony
    0.37
     interse
    0.37
     ወቅት
    0.36
    kube
    0.35
    ered
    0.35
    POSITIVE LOGITS
     Phoenix
    1.08
    Phoenix
    1.04
     phoenix
    0.88
    凰
    0.80
     phe
    0.77
     Phoen
    0.77
    鳳
    0.75
     Suns
    0.74
     Phe
    0.73
     Phen
    0.72
    Act Density 0.004%

    No Known Activations