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

    Neuronpedia

    INDEX
    Explanations

    Court

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Racing
    -0.07
    Made
    -0.06
     Пет
    -0.06
    国产
    -0.06
     Ramos
    -0.06
     Ferr
    -0.06
    lemetry
    -0.06
    erif
    -0.06
    シェ
    -0.06
    licts
    -0.06
    POSITIVE LOGITS
     turbulent
    0.08
     dob
    0.06
     pueda
    0.06
    activate
    0.06
    마
    0.06
     colourful
    0.06
     чес
    0.06
     unclear
    0.06
    itou
    0.06
     gripping
    0.06
    Act Density 0.001%

    No Known Activations