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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ont
    -0.07
     gy
    -0.06
     سخ
    -0.06
    ترین
    -0.06
     Tarih
    -0.06
     віднос
    -0.06
     roku
    -0.06
     NDP
    -0.06
    okies
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    .-
    0.07
     factory
    0.07
     Dumpster
    0.06
     blister
    0.06
     scouting
    0.06
    (logger
    0.06
    abric
    0.06
    аж
    0.06
    能够
    0.06
    CompanyName
    0.06
    Act Density 0.047%

    No Known Activations