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

    Neuronpedia

    INDEX
    Explanations

    cars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     large
    -0.07
    >r
    -0.07
     largely
    -0.07
     ]]↵
    -0.07
     Ты
    -0.06
     tus
    -0.06
    Cx
    -0.06
    activity
    -0.06
    *cos
    -0.06
    (Route
    -0.06
    POSITIVE LOGITS
    。而
    0.07
    lack
    0.06
    ức
    0.06
     Shake
    0.06
     whipping
    0.06
     волод
    0.06
     aplik
    0.06
     крем
    0.06
     μά
    0.06
    ementia
    0.06
    Act Density 0.207%

    No Known Activations