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

    Neuronpedia

    INDEX
    Explanations

    201

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mature
    -0.07
    frontend
    -0.06
     communism
    -0.06
     phương
    -0.06
     sıra
    -0.06
    Tor
    -0.06
    vio
    -0.06
    าหาร
    -0.06
    一些
    -0.06
    totals
    -0.06
    POSITIVE LOGITS
     scientific
    0.07
     -------------------------------------------------------------------------↵
    0.07
     Phrase
    0.06
     packing
    0.06
     triển
    0.06
    Listening
    0.06
     bonded
    0.06
    (resp
    0.06
     розрахун
    0.06
     Pal
    0.06
    Act Density 0.004%

    No Known Activations