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

    Neuronpedia

    INDEX
    Explanations

    Late Victorian or Edwardian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AC
    0.38
    zeugung
    0.37
     scalable
    0.36
     concerning
    0.35
     savings
    0.35
     AU
    0.35
     servicing
    0.35
     television
    0.34
     purpose
    0.34
     surfboard
    0.34
    POSITIVE LOGITS
    চন্দ্রের
    0.37
     hadn
    0.36
     近
    0.36
    ந்திரன்
    0.36
     опубли
    0.36
    MaxIntensity
    0.35
     Prony
    0.35
    獄
    0.34
     劉
    0.33
    巒
    0.33
    Act Density 0.000%

    No Known Activations